greglu-solr-ruby 0.0.7

data/script/setup.rb

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+# 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.
+
+include Solr

data/script/solrshell

@@ -0,0 +1,18 @@
+#!/usr/bin/env ruby
+# 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.
+
+solr_lib   = File.dirname(__FILE__) + '/../lib/solr'
+setup    = File.dirname(__FILE__) + '/setup'
+irb_name = RUBY_PLATFORM =~ /mswin32/ ? 'irb.bat' : 'irb'
+
+exec "#{irb_name} -r #{solr_lib} -r #{setup} --simple-prompt"

data/solr-ruby.gemspec

@@ -0,0 +1,26 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{solr-ruby}
+  s.version = "0.0.7"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Apache Solr"]
+  s.date = %q{2009-03-06}
+  s.description = %q{solr-ruby exposes the power of Solr as a Ruby DSL (domain specific language).}
+  s.email = %q{ruby-dev@lucene.apache.org}
+  s.extra_rdoc_files = ["README", "LICENSE.txt"]
+  s.files = ["solr", "solr/conf", "solr/conf/xslt", "solr/conf/xslt/example.xsl", "solr/conf/schema.xml", "solr/conf/protwords.txt", "solr/conf/stopwords.txt", "solr/conf/solrconfig.xml", "solr/conf/scripts.conf", "solr/conf/admin-extra.html", "solr/conf/synonyms.txt", "test", "test/unit", "test/unit/standard_response_test.rb", "test/unit/document_test.rb", "test/unit/select_test.rb", "test/unit/delimited_file_source_test.rb", "test/unit/xpath_test_file.xml", "test/unit/array_mapper_test.rb", "test/unit/solr_mock_base.rb", "test/unit/field_test.rb", "test/unit/modify_document_test.rb", "test/unit/add_document_test.rb", "test/unit/xpath_mapper_test.rb", "test/unit/request_test.rb", "test/unit/commit_test.rb", "test/unit/suite.rb", "test/unit/changes_yaml_test.rb", "test/unit/spellcheck_response_test.rb", "test/unit/ping_test.rb", "test/unit/dismax_request_test.rb", "test/unit/indexer_test.rb", "test/unit/response_test.rb", "test/unit/connection_test.rb", "test/unit/delete_test.rb", "test/unit/tab_delimited.txt", "test/unit/hpricot_test_file.xml", "test/unit/standard_request_test.rb", "test/unit/hpricot_mapper_test.rb", "test/unit/spellchecker_request_test.rb", "test/unit/data_mapper_test.rb", "test/unit/util_test.rb", "test/functional", "test/functional/test_solr_server.rb", "test/functional/server_test.rb", "test/conf", "test/conf/schema.xml", "test/conf/protwords.txt", "test/conf/stopwords.txt", "test/conf/solrconfig.xml", "test/conf/scripts.conf", "test/conf/admin-extra.html", "test/conf/synonyms.txt", "script", "script/setup.rb", "script/solrshell", "lib", "lib/solr", "lib/solr/importer", "lib/solr/importer/delimited_file_source.rb", "lib/solr/importer/solr_source.rb", "lib/solr/importer/array_mapper.rb", "lib/solr/importer/mapper.rb", "lib/solr/importer/xpath_mapper.rb", "lib/solr/importer/hpricot_mapper.rb", "lib/solr/request", "lib/solr/request/ping.rb", "lib/solr/request/spellcheck.rb", "lib/solr/request/select.rb", "lib/solr/request/optimize.rb", "lib/solr/request/standard.rb", "lib/solr/request/delete.rb", "lib/solr/request/index_info.rb", "lib/solr/request/update.rb", "lib/solr/request/dismax.rb", "lib/solr/request/modify_document.rb", "lib/solr/request/add_document.rb", "lib/solr/request/commit.rb", "lib/solr/request/base.rb", "lib/solr/response", "lib/solr/response/ping.rb", "lib/solr/response/spellcheck.rb", "lib/solr/response/select.rb", "lib/solr/response/optimize.rb", "lib/solr/response/standard.rb", "lib/solr/response/xml.rb", "lib/solr/response/ruby.rb", "lib/solr/response/delete.rb", "lib/solr/response/index_info.rb", "lib/solr/response/dismax.rb", "lib/solr/response/modify_document.rb", "lib/solr/response/add_document.rb", "lib/solr/response/commit.rb", "lib/solr/response/base.rb", "lib/solr/util.rb", "lib/solr/document.rb", "lib/solr/exception.rb", "lib/solr/indexer.rb", "lib/solr/response.rb", "lib/solr/connection.rb", "lib/solr/xml.rb", "lib/solr/importer.rb", "lib/solr/field.rb", "lib/solr/solrtasks.rb", "lib/solr/request.rb", "lib/solr.rb", "examples", "examples/marc", "examples/marc/marc_importer.rb", "examples/delicious_library", "examples/delicious_library/sample_export.txt", "examples/delicious_library/dl_importer.rb", "examples/tang", "examples/tang/tang_importer.rb", "LICENSE.txt", "Rakefile", "CHANGES.yml", "README", "solr-ruby.gemspec"]
+  s.has_rdoc = true
+  s.homepage = %q{http://github.com/greglu/solr-ruby}
+  s.rdoc_options = ["--inline-source", "--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = %q{solr-ruby}
+  s.rubygems_version = %q{1.3.0}
+  s.summary = %q{Ruby library for working with Apache Solr. Packaged and maintained on github by greglu}
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 2
+  end
+end

data/solr/conf/admin-extra.html

@@ -0,0 +1,31 @@
+<!--
+ 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.
+-->
+
+<!-- The content of this page will be statically included into the top
+of the admin page.  Uncomment this as an example to see there the content
+will show up.
+
+<hr>
+<i>This line will appear before the first table</i>
+<tr>
+<td colspan="2">
+This row will be appended to the end of the first table
+</td>
+</tr>
+<hr>
+
+-->

data/solr/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
+

data/solr/conf/schema.xml

@@ -0,0 +1,221 @@
+<?xml version="1.0" ?>
+<!--
+ 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.
+-->
+
+<!-- This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default) 
+ or located where the classloader for the Solr webapp can find it.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+-->
+
+<schema name="flare" version="1.1">
+  <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       Applications should change this to reflect the nature of the search collection.
+       version="1.1" is Solr's version number for the schema syntax and semantics.  It should
+       not normally be changed by applications.
+       1.0: multiValued attribute did not exist, all fields are multiValued by nature
+       1.1: multiValued attribute introduced, false by default -->
+
+  <types>
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldtype.
+         Class names starting with "solr" refer to java classes in the
+       org.apache.solr.analysis package.
+    -->
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.  
+       - StrField and TextField support an optional compressThreshold which
+       limits compression (if enabled in the derived fields) to values which
+       exceed a certain size (in characters).
+    -->
+    <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldtype name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
+
+    <!-- The optional sortMissingLast and sortMissingFirst attributes are
+         currently supported on types that are sorted internally as strings.
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->    
+
+
+    <!-- numeric field types that store and index the text
+         value verbatim (and hence don't support range queries, since the
+         lexicographic ordering isn't equal to the numeric ordering) -->
+    <fieldtype name="integer" class="solr.IntField" omitNorms="true"/>
+    <fieldtype name="long" class="solr.LongField" omitNorms="true"/>
+    <fieldtype name="float" class="solr.FloatField" omitNorms="true"/>
+    <fieldtype name="double" class="solr.DoubleField" omitNorms="true"/>
+
+
+    <!-- Numeric field types that manipulate the value into
+         a string value that isn't human-readable in its internal form,
+         but with a lexicographic ordering the same as the numeric ordering,
+         so that range queries work correctly. -->
+    <fieldtype name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
+    <fieldtype name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
+    <fieldtype name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
+    <fieldtype name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
+
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime    
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+                      
+         Consult the DateField javadocs for more information.
+      -->
+    <fieldtype name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element
+    <fieldtype name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldtype>
+
+    <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StandardFilterFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldtype>
+    
+    <fieldtype name="text_zh" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.cn.ChineseAnalyzer"/>
+    </fieldtype>
+
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <fieldtype name="textTight" class="solr.TextField" positionIncrementGap="100" >
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldtype>
+
+ </types>
+
+
+ <fields>
+   <!-- Valid attributes for fields:
+     name: mandatory - the name for the field
+     type: mandatory - the name of a previously defined type from the <types> section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     compressed: [false] if this field should be stored using gzip compression
+       (this will only apply if the field type is compressable; among
+       the standard field types, only TextField and StrField are)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+   -->
+
+   <field name="id" type="string" indexed="true" stored="true"/>
+
+   <!-- catchall field, containing all other searchable text fields (implemented
+        via copyField further on in this schema  -->
+   <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
+
+   <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
+        will be used if the name matches any of the patterns.
+        RESTRICTION: the glob-like pattern in the name attribute must have
+        a "*" only at the start or the end.
+        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+        Longer patterns will be matched first.  if equal size patterns
+        both match, the first appearing in the schema will be used.  -->
+   <dynamicField name="*_facet"  type="string"  indexed="true"  stored="true" multiValued="true"/>
+   <dynamicField name="*_zh_text"   type="text_zh"    indexed="true"  stored="true" multiValued="true"/>
+   <dynamicField name="*_text"   type="text"    indexed="true"  stored="true" multiValued="true"/>
+   <dynamicField name="*_display"   type="text"    indexed="false"  stored="true" multiValued="true"/>   
+ </fields>
+
+ <!-- field to use to determine and enforce document uniqueness. -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- field for the QueryParser to use when an explicit fieldname is absent -->
+ <defaultSearchField>text</defaultSearchField>
+
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
+ <solrQueryParser defaultOperator="AND"/>
+
+  <!-- copyField commands copy one field to another at the time a document
+        is added to the index.  It's used either to index the same field differently,
+        or to add multiple fields to the same field for easier/faster searching.  -->
+ <copyField source="*_text" dest="text"/>
+ <copyField source="*_facet" dest="text"/>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+      A custom similarity may be specified here, but the default is fine
+      for most applications.  -->
+ <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
+
+</schema>

data/solr/conf/scripts.conf

@@ -0,0 +1,24 @@
+# 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.
+
+user=
+solr_hostname=localhost
+solr_port=8983
+rsyncd_port=18983
+data_dir=
+webapp_name=solr
+master_host=
+master_data_dir=
+master_status_dir=

data/solr/conf/solrconfig.xml

@@ -0,0 +1,394 @@
+<?xml version="1.0" ?>
+<!--
+ 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/data}</dataDir>
+
+  <indexDefaults>
+   <!-- Values here affect all index writers and act as a default unless overridden. -->
+    <useCompoundFile>false</useCompoundFile>
+    <ramBufferSizeMB>32</ramBufferSizeMB>
+    <mergeFactor>10</mergeFactor>
+    <maxMergeDocs>2147483647</maxMergeDocs>
+    <maxFieldLength>10000</maxFieldLength>
+    <writeLockTimeout>1000</writeLockTimeout>
+    <commitLockTimeout>10000</commitLockTimeout>
+  </indexDefaults>
+
+  <mainIndex>
+    <!-- options specific to the main on-disk lucene index -->
+    <useCompoundFile>false</useCompoundFile>
+    <ramBufferSizeMB>32</ramBufferSizeMB>
+    <mergeFactor>10</mergeFactor>
+    <maxMergeDocs>2147483647</maxMergeDocs>
+    <maxFieldLength>10000</maxFieldLength>
+
+    <!-- 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. -->
+    <unlockOnStartup>false</unlockOnStartup>
+  </mainIndex>
+
+  <!-- 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.
+    -->
+    <enableLazyFieldLoading>false</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 values for query parameters -->
+     <lst name="defaults">
+       <str name="echoParams">explicit</str>
+       <!-- 
+       <int name="rows">10</int>
+       <str name="fl">*</str>
+       <str name="version">2.1</str>
+        -->
+     </lst>
+  </requestHandler>
+
+
+
+
+  <requestHandler name="browse" class="solr.DisMaxRequestHandler" >
+    <lst name="defaults">
+     <str name="echoParams">explicit</str>
+     <str name="qf">text^1.0 title_text^2.0 description_text^1.5 id^10.0</str>
+     <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
+     <str name="q.alt">*:*</str>
+    </lst>
+    <!-- In addition to defaults, "appends" params can be specified
+         to identify values which should be appended to the list of
+         multi-val params from the query (or the existing "defaults").
+
+         In this example, the param "fq=instock:true" will be appended to
+         any query time fq params the user may specify, as a mechanism for
+         partitioning the index, independent of any user selected filtering
+         that may also be desired (perhaps as a result of faceted searching).
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "appends" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <lst name="appends">
+    </lst>
+    <!-- "invariants" are a way of letting the Solr maintainer lock down
+         the options available to Solr clients.  Any params values
+         specified here are used regardless of what values may be specified
+         in either the query, the "defaults", or the "appends" params.
+
+         In this example, the facet.field and facet.query params are fixed,
+         limiting the facets clients can use.  Faceting is not turned on by
+         default - but if the client does specify facet=true in the request,
+         these are the only facets they will be able to see counts for;
+         regardless of what other facet.field or facet.query params they
+         may specify.
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "invariants" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <lst name="invariants">
+	  <str name="facet">on</str>
+	  <str name="facet.mincount">1</str>
+      <str name="facet.field">genre_facet</str>
+      <str name="facet.field">medium_facet</str>
+      <str name="facet.field">rating_facet</str>
+      <str name="facet.field">publisher_facet</str>
+    </lst>
+  </requestHandler>
+
+
+  <!-- SpellCheckerRequestHandler takes in a word (or several words) as the
+       value of the "q" parameter and returns a list of alternative spelling
+       suggestions.  If invoked with a ...&cmd=rebuild, it will rebuild the
+       spellchecker index.
+  -->
+  <requestHandler name="spellchecker" class="solr.SpellCheckerRequestHandler">
+    <!-- default values for query parameters -->
+     <lst name="defaults">
+       <int name="suggestionCount">1</int>
+       <float name="accuracy">0.5</float>
+     </lst>
+     
+     <!-- Main init params for handler -->
+     
+     <!-- The directory where your SpellChecker Index should live.   -->
+     <!-- May be absolute, or relative to the Solr "dataDir" directory. -->
+     <!-- If this option is not specified, a RAM directory will be used -->
+     <str name="spellcheckerIndexDir">spell</str>
+     
+     <!-- the field in your schema that you want to be able to build -->
+     <!-- your spell index on. This should be a field that uses a very -->
+     <!-- simple FieldType without a lot of Analysis (ie: string) -->
+     <str name="termSourceField">word</str>
+     
+   </requestHandler>
+
+  
+  <!-- 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" />
+
+  <!-- CSV update handler, loaded on demand -->
+  <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" />
+
+  <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
+  
+  <!-- Echo the request contents back to the client -->
+  <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
+    <lst name="defaults">
+     <str name="echoParams">explicit</str> <!-- for all params (including the default etc) use: 'all' -->
+     <str name="echoHandler">true</str>
+    </lst>
+  </requestHandler>
+  
+  <!-- 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 for the admin interface --> 
+  <admin>
+    <defaultQuery>solr</defaultQuery>
+    <!-- configure a healthcheck file for servers behind a loadbalancer
+    <healthcheck type="file">server-enabled</healthcheck>
+    -->
+  </admin>
+
+</config>