muck-raker 0.1.13 → 0.1.14

data/test/rails_root/config/solr/cores/de/conf/solrconfig.xml

@@ -0,0 +1,304 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ 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.
+-->
+
+<config>
+  <!-- Set this to 'false' if you want solr to continue working after it has 
+       encountered an severe configuration error.  In a production environment, 
+       you may want solr to keep working even if one handler is mis-configured.
+
+       You may also set this to false using by setting the system property:
+         -Dsolr.abortOnConfigurationError=false
+     -->
+  <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
+
+  <!-- Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.
+       If replication is in use, this should match the replication configuration. -->
+  <dataDir>${solr.data.dir:../../../../../solr_indexes}/de</dataDir>
+
+   <!-- Values here affect all index writers and act as a default unless overridden. -->
+  <indexDefaults>
+    <useCompoundFile>false</useCompoundFile>
+    <mergeFactor>10</mergeFactor>
+    <maxBufferedDocs>1000</maxBufferedDocs>
+    <maxMergeDocs>2147483647</maxMergeDocs>
+    <maxFieldLength>10000</maxFieldLength>
+    <writeLockTimeout>1000</writeLockTimeout>
+    <commitLockTimeout>10000</commitLockTimeout>
+  </indexDefaults>
+    <!-- options specific to the main on-disk lucene index -->
+<!--
+  <mainIndex>
+    <useCompoundFile>false</useCompoundFile>
+    <mergeFactor>10</mergeFactor>
+    <maxBufferedDocs>1000</maxBufferedDocs>
+    <maxMergeDocs>2147483647</maxMergeDocs>
+    <maxFieldLength>10000</maxFieldLength>
+
+    <unlockOnStartup>false</unlockOnStartup>
+  </mainIndex>
+-->
+    <!-- If true, unlock any held write or commit locks on startup. 
+         This defeats the locking mechanism that allows multiple
+         processes to safely access a lucene index, and should be
+         used with care. -->
+
+  <!-- the default high-performance update handler -->
+
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- A prefix of "solr." for class names is an alias that
+         causes solr to search appropriate packages, including
+         org.apache.solr.(search|update|request|core|analysis)
+     -->
+
+    <!-- autocommit pending docs if certain criteria are met 
+    <autoCommit> 
+      <maxDocs>10000</maxDocs>
+      <maxTime>1000</maxTime>
+    </autoCommit>
+    -->
+
+    <!-- The RunExecutableListener executes an external command.
+         exe - the name of the executable to run
+         dir - dir to use as the current working directory. default="."
+         wait - the calling thread waits until the executable returns. default="true"
+         args - the arguments to pass to the program.  default=nothing
+         env - environment variables to set.  default=nothing
+      -->
+    <!-- A postCommit event is fired after every commit or optimize command
+    <listener event="postCommit" class="solr.RunExecutableListener">
+      <str name="exe">snapshooter</str>
+      <str name="dir">solr/bin</str>
+      <bool name="wait">true</bool>
+      <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
+      <arr name="env"> <str>MYVAR=val1</str> </arr>
+    </listener>
+    -->
+    <!-- A postOptimize event is fired only after every optimize command, useful
+         in conjunction with index distribution to only distribute optimized indicies 
+    <listener event="postOptimize" class="solr.RunExecutableListener">
+      <str name="exe">snapshooter</str>
+      <str name="dir">solr/bin</str>
+      <bool name="wait">true</bool>
+    </listener>
+    -->
+
+  </updateHandler>
+
+
+  <query>
+    <!-- Maximum number of clauses in a boolean query... can affect
+        range or prefix queries that expand to big boolean
+        queries.  An exception is thrown if exceeded.  -->
+    <maxBooleanClauses>1024</maxBooleanClauses>
+
+    
+    <!-- Cache used by SolrIndexSearcher for filters (DocSets),
+         unordered sets of *all* documents that match a query.
+         When a new searcher is opened, its caches may be prepopulated
+         or "autowarmed" using data from caches in the old searcher.
+         autowarmCount is the number of items to prepopulate.  For LRUCache,
+         the autowarmed items will be the most recently accessed items.
+       Parameters:
+         class - the SolrCache implementation (currently only LRUCache)
+         size - the maximum number of entries in the cache
+         initialSize - the initial capacity (number of entries) of
+           the cache.  (seel java.util.HashMap)
+         autowarmCount - the number of entries to prepopulate from
+           and old cache.
+         -->
+    <filterCache
+      class="solr.LRUCache"
+      size="512"
+      initialSize="512"
+      autowarmCount="256"/>
+
+   <!-- queryResultCache caches results of searches - ordered lists of
+         document ids (DocList) based on a query, a sort, and the range
+         of documents requested.  -->
+    <queryResultCache
+      class="solr.LRUCache"
+      size="512"
+      initialSize="512"
+      autowarmCount="256"/>
+
+  <!-- documentCache caches Lucene Document objects (the stored fields for each document).
+       Since Lucene internal document ids are transient, this cache will not be autowarmed.  -->
+    <documentCache
+      class="solr.LRUCache"
+      size="512"
+      initialSize="512"
+      autowarmCount="0"/>
+
+    <!-- If true, stored fields that are not requested will be loaded lazily.
+
+    This can result in a significant speed improvement if the usual case is to
+    not load all stored fields, especially if the skipped fields are large compressed
+    text fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!-- Example of a generic cache.  These caches may be accessed by name
+         through SolrIndexSearcher.getCache(),cacheLookup(), and cacheInsert().
+         The purpose is to enable easy caching of user/application level data.
+         The regenerator argument should be specified as an implementation
+         of solr.search.CacheRegenerator if autowarming is desired.  -->
+    <!--
+    <cache name="myUserCache"
+      class="solr.LRUCache"
+      size="4096"
+      initialSize="1024"
+      autowarmCount="1024"
+      regenerator="org.mycompany.mypackage.MyRegenerator"
+      />
+    -->
+
+   <!-- An optimization that attempts to use a filter to satisfy a search.
+         If the requested sort does not include score, then the filterCache
+         will be checked for a filter matching the query. If found, the filter
+         will be used as the source of document ids, and then the sort will be
+         applied to that.
+    <useFilterForSortedQuery>true</useFilterForSortedQuery>
+   -->
+
+   <!-- An optimization for use with the queryResultCache.  When a search
+         is requested, a superset of the requested number of document ids
+         are collected.  For example, if a search for a particular query
+         requests matching documents 10 through 19, and queryWindowSize is 50,
+         then documents 0 through 50 will be collected and cached.  Any further
+         requests in that range can be satisfied via the cache.  -->
+    <queryResultWindowSize>10</queryResultWindowSize>
+
+    <!-- This entry enables an int hash representation for filters (DocSets)
+         when the number of items in the set is less than maxSize.  For smaller
+         sets, this representation is more memory efficient, more efficient to
+         iterate over, and faster to take intersections.  -->
+    <HashDocSet maxSize="3000" loadFactor="0.75"/>
+
+
+    <!-- boolToFilterOptimizer converts boolean clauses with zero boost
+         into cached filters if the number of docs selected by the clause exceeds
+         the threshold (represented as a fraction of the total index) -->
+    <boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
+
+
+    <!-- a newSearcher event is fired whenever a new searcher is being prepared
+         and there is a current searcher handling requests (aka registered). -->
+    <!-- QuerySenderListener takes an array of NamedList and executes a
+         local query request for each NamedList in sequence. -->
+    <!--
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <lst> <str name="q">solr</str> <str name="start">0</str> <str name="rows">10</str> </lst>
+        <lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
+      </arr>
+    </listener>
+    -->
+
+    <!-- a firstSearcher event is fired whenever a new searcher is being
+         prepared but there is no current registered searcher to handle
+         requests or to gain autowarming data from. -->
+    <!--
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
+      </arr>
+    </listener>
+    -->
+
+    <!-- If a search request comes in and there is no current registered searcher,
+         then immediately register the still warming searcher and use it.  If
+         "false" then all requests will block until the first searcher is done
+         warming. -->
+    <useColdSearcher>false</useColdSearcher>
+
+    <!-- Maximum number of searchers that may be warming in the background
+      concurrently.  An error is returned if this limit is exceeded. Recommend
+      1-2 for read-only slaves, higher for masters w/o cache warming. -->
+    <maxWarmingSearchers>4</maxWarmingSearchers>
+
+  </query>
+
+  <!-- 
+    Let the dispatch filter handler /select?qt=XXX
+    handleSelect=true will use consistent error handling for /select and /update
+    handleSelect=false will use solr1.1 style error formatting
+    -->
+  <requestDispatcher handleSelect="true" >
+    <!--Make sure your system has some authentication before enabling remote streaming!  -->
+    <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+  </requestDispatcher>
+  
+      
+  <!-- requestHandler plugins... incoming queries will be dispatched to the
+     correct handler based on the qt (query type) param matching the
+     name of registered handlers.
+     The "standard" request handler is the default and will be used if qt
+     is not specified in the request.
+  -->
+  <requestHandler name="standard" class="solr.StandardRequestHandler" default="true">
+    <!-- default values for query parameters -->
+     <lst name="defaults">
+       <str name="echoParams">explicit</str>
+	   <str name="json.nl">map</str>
+       <!-- 
+       <int name="rows">10</int>
+       <str name="fl">*</str>
+       <str name="version">2.1</str>
+        -->
+     </lst>
+  </requestHandler>
+
+  <!-- Note how you can register the same handler multiple times with
+       different names (and different init parameters)
+    -->
+  <!-- Update request handler.  
+  
+       Note: Since solr1.1 requestHandlers requires a valid content type header if posted in 
+       the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8'
+       The response format differs from solr1.1 formatting and returns a standard error code.
+       
+       To enable solr1.1 behavior, remove the /update handler or change its path
+  <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
+    -->
+
+  <!-- queryResponseWriter plugins... query responses will be written using the
+    writer specified by the 'wt' request parameter matching the name of a registered
+    writer.
+    The "standard" writer is the default and will be used if 'wt' is not specified 
+    in the request. XMLResponseWriter will be used if nothing is specified here.
+    The json, python, and ruby writers are also available by default.
+
+    <queryResponseWriter name="standard" class="org.apache.solr.request.XMLResponseWriter"/>
+    <queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/>
+    <queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/>
+    <queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/>
+
+    <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
+  -->
+
+  <!-- XSLT response writer transforms the XML output by any xslt file found
+       in Solr's conf/xslt directory.  Changes to xslt files are checked for
+       every xsltCacheLifetimeSeconds.  
+   -->
+  <queryResponseWriter name="xslt" class="org.apache.solr.request.XSLTResponseWriter">
+    <int name="xsltCacheLifetimeSeconds">5</int>
+  </queryResponseWriter> 
+    
+</config>

data/test/rails_root/config/solr/cores/de/conf/stopwords.txt

@@ -0,0 +1,341 @@
+# 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.
+
+#-----------------------------------------------------------------------
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+#stopwords list i found on the internet
+a
+about
+above
+across
+after
+afterwards
+again
+against
+all
+almost
+alone
+along
+already
+also
+although
+always
+am
+among
+amongst
+amoungst
+amount
+an
+and
+another
+any
+anyhow
+anyone
+anything
+anyway
+anywhere
+are
+around
+as
+at
+back
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+behind
+being
+below
+beside
+besides
+between
+beyond
+bill
+both
+bottom
+but
+by
+call
+can
+cannot
+cant
+co
+computer
+con
+could
+couldnt
+cry
+de
+describe
+detail
+do
+done
+down
+due
+during
+each
+eg
+eight
+either
+eleven
+else
+elsewhere
+empty
+enough
+etc
+even
+ever
+every
+everyone
+everything
+everywhere
+except
+few
+fifteen
+fify
+fill
+find
+fire
+first
+five
+for
+former
+formerly
+forty
+found
+four
+from
+front
+full
+further
+get
+give
+go
+had
+has
+hasnt
+have
+he
+hence
+her
+here
+hereafter
+hereby
+herein
+hereupon
+hers
+herself
+him
+himself
+his
+how
+however
+hundred
+i
+ie
+if
+in
+inc
+indeed
+interest
+into
+is
+it
+its
+itself
+keep
+last
+latter
+latterly
+least
+less
+ltd
+made
+many
+may
+me
+meanwhile
+might
+mill
+mine
+more
+moreover
+most
+mostly
+move
+much
+must
+my
+myself
+name
+namely
+neither
+never
+nevertheless
+next
+nine
+no
+nobody
+none
+noone
+nor
+not
+nothing
+now
+nowhere
+of
+off
+often
+on
+once
+one
+only
+onto
+or
+other
+others
+otherwise
+our
+ours
+ourselves
+out
+over
+own
+part
+per
+perhaps
+please
+put
+rather
+re
+same
+see
+seem
+seemed
+seeming
+seems
+serious
+several
+she
+should
+show
+side
+since
+sincere
+six
+sixty
+so
+some
+somehow
+someone
+something
+sometime
+sometimes
+somewhere
+still
+such
+system
+take
+ten
+than
+that
+the
+their
+them
+themselves
+then
+thence
+there
+thereafter
+thereby
+therefore
+therein
+thereupon
+these
+they
+thick
+thin
+third
+this
+those
+though
+three
+through
+throughout
+thru
+thus
+to
+together
+too
+top
+toward
+towards
+twelve
+twenty
+two
+un
+under
+until
+up
+upon
+us
+very
+via
+was
+we
+well
+were
+what
+whatever
+when
+whence
+whenever
+where
+whereafter
+whereas
+whereby
+wherein
+whereupon
+wherever
+whether
+which
+while
+whither
+who
+whoever
+whole
+whom
+whose
+why
+will
+with
+within
+without
+would
+yet
+you
+your
+yours
+yourself
+yourselves

data/test/rails_root/config/solr/cores/de/conf/synonyms.txt

@@ -0,0 +1,31 @@
+# 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.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaa => aaaa
+bbb => bbbb1 bbbb2
+ccc => cccc1,cccc2
+a\=>a => b\=>b
+a\,a => b\,b
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+

data/test/rails_root/config/solr/cores/en/conf/protwords.txt

@@ -0,0 +1,21 @@
+# 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.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+