tmp commit for search. start nccu0621 first
This commit is contained in:
parent
cb17fe0825
commit
3f95fe4f13
5
Gemfile
5
Gemfile
|
@ -37,9 +37,8 @@ gem 'therubyracer' if RUBY_PLATFORM.downcase.include?("linux")
|
|||
|
||||
gem "impressionist", :require => "impressionist", :path => "vendor/impressionist"
|
||||
|
||||
# gem "tire"
|
||||
gem 'sunspot_rails', "~> 1.3.2"
|
||||
gem 'sunspot_solr'
|
||||
gem "tire"
|
||||
|
||||
|
||||
# Gems used only for assets and not required
|
||||
# in production environments by default.
|
||||
|
|
13
Gemfile.lock
13
Gemfile.lock
|
@ -96,6 +96,7 @@ GEM
|
|||
railties (>= 3.0.0)
|
||||
fastercsv (1.5.4)
|
||||
haml (3.1.4)
|
||||
hashr (0.0.21)
|
||||
hike (1.2.1)
|
||||
hoe (2.16.1)
|
||||
rake (~> 0.8)
|
||||
|
@ -185,6 +186,8 @@ GEM
|
|||
redis (>= 2.0.1)
|
||||
resque (>= 1.8.0)
|
||||
rufus-scheduler
|
||||
rest-client (1.6.7)
|
||||
mime-types (>= 1.16)
|
||||
rsolr (1.0.8)
|
||||
builder (>= 2.1.2)
|
||||
rspec (2.8.0)
|
||||
|
@ -253,13 +256,18 @@ GEM
|
|||
sunspot_rails (1.3.3)
|
||||
nokogiri
|
||||
sunspot (= 1.3.3)
|
||||
sunspot_solr (1.3.3)
|
||||
therubyracer (0.9.9)
|
||||
libv8 (~> 3.3.10)
|
||||
thor (0.14.6)
|
||||
tilt (1.3.3)
|
||||
tinymce-rails (3.4.8)
|
||||
railties (>= 3.1)
|
||||
tire (0.4.2)
|
||||
activemodel (>= 3.0)
|
||||
hashr (~> 0.0.19)
|
||||
multi_json (~> 1.0)
|
||||
rake
|
||||
rest-client (~> 1.6)
|
||||
transaction-simple (1.4.0)
|
||||
hoe (>= 1.1.7)
|
||||
treetop (1.4.10)
|
||||
|
@ -327,9 +335,8 @@ DEPENDENCIES
|
|||
spork
|
||||
sprockets
|
||||
sunspot-rails-tester
|
||||
sunspot_rails (~> 1.3.2)
|
||||
sunspot_solr
|
||||
therubyracer
|
||||
tinymce-rails
|
||||
tire
|
||||
uglifier
|
||||
watchr
|
||||
|
|
|
@ -1,46 +0,0 @@
|
|||
# coding: utf-8
|
||||
# 基本 Model,加入一些通用功能
|
||||
module Mongoid
|
||||
module BaseModel
|
||||
extend ActiveSupport::Concern
|
||||
|
||||
included do
|
||||
scope :recent, desc(:_id)
|
||||
scope :exclude_ids, Proc.new { |ids| where(:_id.nin => ids.map(&:to_i)) }
|
||||
scope :by_week, where(:created_at.gte => 7.days.ago.utc)
|
||||
end
|
||||
|
||||
module ClassMethods
|
||||
# like ActiveRecord find_by_id
|
||||
def find_by_id(id)
|
||||
if id.is_a?(Integer) or id.is_a?(String)
|
||||
where(:_id => id.to_i).first
|
||||
else
|
||||
nil
|
||||
end
|
||||
end
|
||||
|
||||
def find_in_batches(opts = {})
|
||||
batch_size = opts[:batch_size] || 1000
|
||||
start = opts.delete(:start).to_i || 0
|
||||
objects = self.limit(batch_size).skip(start)
|
||||
t = Time.new
|
||||
while objects.any?
|
||||
yield objects
|
||||
start += batch_size
|
||||
# Rails.logger.debug("processed #{start} records in #{Time.new - t} seconds") if Rails.logger.debug?
|
||||
break if objects.size < batch_size
|
||||
objects = self.limit(batch_size).skip(start)
|
||||
end
|
||||
end
|
||||
|
||||
def delay
|
||||
Sidekiq::Extensions::Proxy.new(DelayedDocument, self)
|
||||
end
|
||||
end
|
||||
|
||||
def delay
|
||||
Sidekiq::Extensions::Proxy.new(DelayedDocument, self)
|
||||
end
|
||||
end
|
||||
end
|
|
@ -1,46 +0,0 @@
|
|||
# coding: utf-8
|
||||
# this is from : https://github.com/jugyo/sunspot_mongoid
|
||||
# this file is special for mongoid_auto_increment_id
|
||||
require 'sunspot'
|
||||
require 'mongoid'
|
||||
require 'sunspot/rails'
|
||||
|
||||
# == Examples:
|
||||
#
|
||||
# class Post
|
||||
# include Mongoid::Document
|
||||
# field :title
|
||||
#
|
||||
# include Sunspot::Mongoid
|
||||
# searchable do
|
||||
# text :title
|
||||
# end
|
||||
# end
|
||||
#
|
||||
module Sunspot
|
||||
module Mongoid
|
||||
def self.included(base)
|
||||
base.class_eval do
|
||||
extend Sunspot::Rails::Searchable::ActsAsMethods
|
||||
Sunspot::Adapters::DataAccessor.register(DataAccessor, base)
|
||||
Sunspot::Adapters::InstanceAdapter.register(InstanceAdapter, base)
|
||||
end
|
||||
end
|
||||
|
||||
class InstanceAdapter < Sunspot::Adapters::InstanceAdapter
|
||||
def id
|
||||
@instance.id
|
||||
end
|
||||
end
|
||||
|
||||
class DataAccessor < Sunspot::Adapters::DataAccessor
|
||||
def load(id)
|
||||
@clazz.where(:_id => id).first
|
||||
end
|
||||
|
||||
def load_all(ids)
|
||||
@clazz.where(:_id.in => ids.collect { |id| id.to_i })
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
|
@ -5,6 +5,7 @@ num_workers = rails_env == 'production' ? 5 : 2
|
|||
num_workers.times do |num|
|
||||
God.watch do |w|
|
||||
w.dir = "#{rails_root}"
|
||||
w.log = "#{rails_root}/log/myprocess.log"
|
||||
w.name = "resque-#{num}"
|
||||
w.group = 'resque'
|
||||
w.interval = 30.seconds
|
||||
|
|
|
@ -14,7 +14,7 @@ $(document).ready(function() {
|
|||
function ajax_load_proc(wapper,url){
|
||||
wapper.load(url,function(respText,textSta,XML){
|
||||
if(textSta == 'error')
|
||||
wapper.html("Loading Failed");
|
||||
wapper.html("Loading Failed<br/> <a href='"+$(this).attr('path')+"'>Go See</a>");
|
||||
});
|
||||
}
|
||||
|
||||
|
|
|
@ -1,31 +0,0 @@
|
|||
<!--
|
||||
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.
|
||||
-->
|
||||
|
||||
<!-- 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>
|
||||
|
||||
-->
|
|
@ -1,36 +0,0 @@
|
|||
<?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.
|
||||
-->
|
||||
|
||||
<!-- If this file is found in the config directory, it will only be
|
||||
loaded once at startup. If it is found in Solr's data
|
||||
directory, it will be re-loaded every commit.
|
||||
-->
|
||||
|
||||
<elevate>
|
||||
<query text="foo bar">
|
||||
<doc id="1" />
|
||||
<doc id="2" />
|
||||
<doc id="3" />
|
||||
</query>
|
||||
|
||||
<query text="ipod">
|
||||
<doc id="MA147LL/A" /> <!-- put the actual ipod at the top -->
|
||||
<doc id="IW-02" exclude="true" /> <!-- exclude this cable -->
|
||||
</query>
|
||||
|
||||
</elevate>
|
|
@ -1,246 +0,0 @@
|
|||
# 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.
|
||||
|
||||
# Syntax:
|
||||
# "source" => "target"
|
||||
# "source".length() > 0 (source cannot be empty.)
|
||||
# "target".length() >= 0 (target can be empty.)
|
||||
|
||||
# example:
|
||||
# "À" => "A"
|
||||
# "\u00C0" => "A"
|
||||
# "\u00C0" => "\u0041"
|
||||
# "ß" => "ss"
|
||||
# "\t" => " "
|
||||
# "\n" => ""
|
||||
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
|
||||
# Å => A
|
||||
"\u00C5" => "A"
|
||||
|
||||
# Æ => AE
|
||||
"\u00C6" => "AE"
|
||||
|
||||
# Ç => C
|
||||
"\u00C7" => "C"
|
||||
|
||||
# È => E
|
||||
"\u00C8" => "E"
|
||||
|
||||
# É => E
|
||||
"\u00C9" => "E"
|
||||
|
||||
# Ê => E
|
||||
"\u00CA" => "E"
|
||||
|
||||
# Ë => E
|
||||
"\u00CB" => "E"
|
||||
|
||||
# Ì => I
|
||||
"\u00CC" => "I"
|
||||
|
||||
# Í => I
|
||||
"\u00CD" => "I"
|
||||
|
||||
# Î => I
|
||||
"\u00CE" => "I"
|
||||
|
||||
# Ï => I
|
||||
"\u00CF" => "I"
|
||||
|
||||
# IJ => IJ
|
||||
"\u0132" => "IJ"
|
||||
|
||||
# Ð => D
|
||||
"\u00D0" => "D"
|
||||
|
||||
# Ñ => N
|
||||
"\u00D1" => "N"
|
||||
|
||||
# Ò => O
|
||||
"\u00D2" => "O"
|
||||
|
||||
# Ó => O
|
||||
"\u00D3" => "O"
|
||||
|
||||
# Ô => O
|
||||
"\u00D4" => "O"
|
||||
|
||||
# Õ => O
|
||||
"\u00D5" => "O"
|
||||
|
||||
# Ö => O
|
||||
"\u00D6" => "O"
|
||||
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
|
||||
# Ý => Y
|
||||
"\u00DD" => "Y"
|
||||
|
||||
# Ÿ => Y
|
||||
"\u0178" => "Y"
|
||||
|
||||
# à => a
|
||||
"\u00E0" => "a"
|
||||
|
||||
# á => a
|
||||
"\u00E1" => "a"
|
||||
|
||||
# â => a
|
||||
"\u00E2" => "a"
|
||||
|
||||
# ã => a
|
||||
"\u00E3" => "a"
|
||||
|
||||
# ä => a
|
||||
"\u00E4" => "a"
|
||||
|
||||
# å => a
|
||||
"\u00E5" => "a"
|
||||
|
||||
# æ => ae
|
||||
"\u00E6" => "ae"
|
||||
|
||||
# ç => c
|
||||
"\u00E7" => "c"
|
||||
|
||||
# è => e
|
||||
"\u00E8" => "e"
|
||||
|
||||
# é => e
|
||||
"\u00E9" => "e"
|
||||
|
||||
# ê => e
|
||||
"\u00EA" => "e"
|
||||
|
||||
# ë => e
|
||||
"\u00EB" => "e"
|
||||
|
||||
# ì => i
|
||||
"\u00EC" => "i"
|
||||
|
||||
# í => i
|
||||
"\u00ED" => "i"
|
||||
|
||||
# î => i
|
||||
"\u00EE" => "i"
|
||||
|
||||
# ï => i
|
||||
"\u00EF" => "i"
|
||||
|
||||
# ij => ij
|
||||
"\u0133" => "ij"
|
||||
|
||||
# ð => d
|
||||
"\u00F0" => "d"
|
||||
|
||||
# ñ => n
|
||||
"\u00F1" => "n"
|
||||
|
||||
# ò => o
|
||||
"\u00F2" => "o"
|
||||
|
||||
# ó => o
|
||||
"\u00F3" => "o"
|
||||
|
||||
# ô => o
|
||||
"\u00F4" => "o"
|
||||
|
||||
# õ => o
|
||||
"\u00F5" => "o"
|
||||
|
||||
# ö => o
|
||||
"\u00F6" => "o"
|
||||
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
|
||||
# ý => y
|
||||
"\u00FD" => "y"
|
||||
|
||||
# ÿ => y
|
||||
"\u00FF" => "y"
|
||||
|
||||
# ff => ff
|
||||
"\uFB00" => "ff"
|
||||
|
||||
# fi => fi
|
||||
"\uFB01" => "fi"
|
||||
|
||||
# fl => fl
|
||||
"\uFB02" => "fl"
|
||||
|
||||
# ffi => ffi
|
||||
"\uFB03" => "ffi"
|
||||
|
||||
# ffl => ffl
|
||||
"\uFB04" => "ffl"
|
||||
|
||||
# ſt => ft
|
||||
"\uFB05" => "ft"
|
||||
|
||||
# st => st
|
||||
"\uFB06" => "st"
|
|
@ -1,21 +0,0 @@
|
|||
# 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
|
||||
|
|
@ -1,245 +0,0 @@
|
|||
<?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.
|
||||
-->
|
||||
<!--
|
||||
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.
|
||||
|
||||
This example schema is the recommended starting point for users.
|
||||
It should be kept correct and concise, usable out-of-the-box.
|
||||
|
||||
For more information, on how to customize this file, please see
|
||||
http://wiki.apache.org/solr/SchemaXml
|
||||
|
||||
PERFORMANCE NOTE: this schema includes many optional features and should not
|
||||
be used for benchmarking. To improve performance one could
|
||||
- set stored="false" for all fields possible (esp large fields) when you
|
||||
only need to search on the field but don't need to return the original
|
||||
value.
|
||||
- set indexed="false" if you don't need to search on the field, but only
|
||||
return the field as a result of searching on other indexed fields.
|
||||
- remove all unneeded copyField statements
|
||||
- for best index size and searching performance, set "index" to false
|
||||
for all general text fields, use copyField to copy them to the
|
||||
catchall "text" field, and use that for searching.
|
||||
- For maximum indexing performance, use the StreamingUpdateSolrServer
|
||||
java client.
|
||||
- Remember to run the JVM in server mode, and use a higher logging level
|
||||
that avoids logging every request
|
||||
-->
|
||||
<schema name="sunspot" version="1.0">
|
||||
<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.
|
||||
-->
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="string" class="solr.StrField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="tdouble" class="solr.TrieDoubleField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="text" class="solr.TextField" omitNorms="false">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.CJKTokenizerFactory"/>
|
||||
<filter class="solr.StandardFilterFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="15"/>
|
||||
</analyzer>
|
||||
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StandardFilterFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="boolean" class="solr.BoolField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="date" class="solr.DateField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="sdouble" class="solr.SortableDoubleField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="sfloat" class="solr.SortableFloatField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="sint" class="solr.SortableIntField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="slong" class="solr.SortableLongField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="tint" class="solr.TrieIntField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="tfloat" class="solr.TrieFloatField" omitNorms="true"/>
|
||||
<!-- *** This fieldType is used by Sunspot! *** -->
|
||||
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true"/>
|
||||
</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.
|
||||
termVectors: [false] set to true to store the term vector for a
|
||||
given field.
|
||||
When using MoreLikeThis, fields used for similarity should be
|
||||
stored for best performance.
|
||||
termPositions: Store position information with the term vector.
|
||||
This will increase storage costs.
|
||||
termOffsets: Store offset information with the term vector. This
|
||||
will increase storage costs.
|
||||
default: a value that should be used if no value is specified
|
||||
when adding a document.
|
||||
-->
|
||||
<!-- *** This field is used by Sunspot! *** -->
|
||||
<field name="id" stored="true" type="string" multiValued="false" indexed="true"/>
|
||||
<!-- *** This field is used by Sunspot! *** -->
|
||||
<field name="type" stored="false" type="string" multiValued="true" indexed="true"/>
|
||||
<!-- *** This field is used by Sunspot! *** -->
|
||||
<field name="class_name" stored="false" type="string" multiValued="false" indexed="true"/>
|
||||
<!-- *** This field is used by Sunspot! *** -->
|
||||
<field name="text" stored="false" type="string" multiValued="true" indexed="true"/>
|
||||
<!-- *** This field is used by Sunspot! *** -->
|
||||
<field name="lat" stored="true" type="tdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This field is used by Sunspot! *** -->
|
||||
<field name="lng" stored="true" type="tdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="random_*" stored="false" type="rand" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="_local*" stored="false" type="tdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_text" stored="false" type="text" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_texts" stored="true" type="text" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_b" stored="false" type="boolean" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_bm" stored="false" type="boolean" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_bs" stored="true" type="boolean" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_bms" stored="true" type="boolean" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_d" stored="false" type="date" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_dm" stored="false" type="date" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ds" stored="true" type="date" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_dms" stored="true" type="date" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_e" stored="false" type="sdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_em" stored="false" type="sdouble" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_es" stored="true" type="sdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ems" stored="true" type="sdouble" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_f" stored="false" type="sfloat" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_fm" stored="false" type="sfloat" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_fs" stored="true" type="sfloat" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_fms" stored="true" type="sfloat" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_i" stored="false" type="sint" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_im" stored="false" type="sint" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_is" stored="true" type="sint" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ims" stored="true" type="sint" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_l" stored="false" type="slong" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_lm" stored="false" type="slong" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ls" stored="true" type="slong" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_lms" stored="true" type="slong" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_s" stored="false" type="string" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_sm" stored="false" type="string" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ss" stored="true" type="string" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_sms" stored="true" type="string" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_it" stored="false" type="tint" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_itm" stored="false" type="tint" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_its" stored="true" type="tint" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_itms" stored="true" type="tint" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ft" stored="false" type="tfloat" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ftm" stored="false" type="tfloat" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_fts" stored="true" type="tfloat" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ftms" stored="true" type="tfloat" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_dt" stored="false" type="tdate" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_dtm" stored="false" type="tdate" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_dts" stored="true" type="tdate" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_dtms" stored="true" type="tdate" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_textv" stored="false" termVectors="true" type="text" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_textsv" stored="true" termVectors="true" type="text" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_et" stored="false" termVectors="true" type="tdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_etm" stored="false" termVectors="true" type="tdouble" multiValued="true" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_ets" stored="true" termVectors="true" type="tdouble" multiValued="false" indexed="true"/>
|
||||
<!-- *** This dynamicField is used by Sunspot! *** -->
|
||||
<dynamicField name="*_etms" stored="true" termVectors="true" type="tdouble" multiValued="true" indexed="true"/>
|
||||
</fields>
|
||||
<!-- Field to use to determine and enforce document uniqueness.
|
||||
Unless this field is marked with required="false", it will be a required field
|
||||
-->
|
||||
<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. -->
|
||||
</schema>
|
|
@ -1,24 +0,0 @@
|
|||
# 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.
|
||||
|
||||
user=
|
||||
solr_hostname=localhost
|
||||
solr_port=8983
|
||||
rsyncd_port=18983
|
||||
data_dir=
|
||||
webapp_name=solr
|
||||
master_host=
|
||||
master_data_dir=
|
||||
master_status_dir=
|
|
@ -1,938 +0,0 @@
|
|||
<?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.
|
||||
-->
|
||||
<!--
|
||||
For more details about configurations options that may appear in this
|
||||
file, see http://wiki.apache.org/solr/SolrConfigXml.
|
||||
|
||||
Specifically, the Solr Config can support XInclude, which may make it easier to manage
|
||||
the configuration. See https://issues.apache.org/jira/browse/SOLR-1167
|
||||
-->
|
||||
<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>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
|
||||
<!-- lib directives can be used to instruct Solr to load an Jars identified
|
||||
and use them to resolve any "plugins" specified in your solrconfig.xml or
|
||||
schema.xml (ie: Analyzers, Request Handlers, etc...).
|
||||
|
||||
All directories and paths are resolved relative the instanceDir.
|
||||
|
||||
If a "./lib" directory exists in your instanceDir, all files found in it
|
||||
are included as if you had used the following syntax...
|
||||
|
||||
<lib dir="./lib" />
|
||||
-->
|
||||
<!-- A dir option by itself adds any files found in the directory to the
|
||||
classpath, this is useful for including all jars in a directory.
|
||||
-->
|
||||
<lib dir="../../contrib/extraction/lib"/>
|
||||
<!-- When a regex is specified in addition to a directory, only the files in that
|
||||
directory which completely match the regex (anchored on both ends)
|
||||
will be included.
|
||||
-->
|
||||
<lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar"/>
|
||||
<lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar"/>
|
||||
<!-- If a dir option (with or without a regex) is used and nothing is found
|
||||
that matches, it will be ignored
|
||||
-->
|
||||
<lib dir="../../contrib/clustering/lib/downloads/"/>
|
||||
<lib dir="../../contrib/clustering/lib/"/>
|
||||
<lib dir="/total/crap/dir/ignored"/>
|
||||
<!-- an exact path can be used to specify a specific file. This will cause
|
||||
a serious error to be logged if it can't be loaded.
|
||||
<lib path="../a-jar-that-does-not-exist.jar" />
|
||||
-->
|
||||
<!-- Used to specify an alternate directory to hold all index data
|
||||
other than the default ./data under the Solr home.
|
||||
If replication is in use, this should match the replication configuration. -->
|
||||
<dataDir>${solr.data.dir:./solr/data}</dataDir>
|
||||
<!-- WARNING: this <indexDefaults> section only provides defaults for index writers
|
||||
in general. See also the <mainIndex> section after that when changing parameters
|
||||
for Solr's main Lucene index. -->
|
||||
<indexDefaults>
|
||||
<!-- Values here affect all index writers and act as a default unless overridden. -->
|
||||
<useCompoundFile>false</useCompoundFile>
|
||||
<mergeFactor>10</mergeFactor>
|
||||
<!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush
|
||||
based on whichever limit is hit first. -->
|
||||
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
|
||||
<!-- Sets the amount of RAM that may be used by Lucene indexing
|
||||
for buffering added documents and deletions before they are
|
||||
flushed to the Directory. -->
|
||||
<ramBufferSizeMB>32</ramBufferSizeMB>
|
||||
<!-- <maxMergeDocs>2147483647</maxMergeDocs> -->
|
||||
<maxFieldLength>10000</maxFieldLength>
|
||||
<writeLockTimeout>1000</writeLockTimeout>
|
||||
<commitLockTimeout>10000</commitLockTimeout>
|
||||
<!--
|
||||
Expert: Turn on Lucene's auto commit capability. This causes intermediate
|
||||
segment flushes to write a new lucene index descriptor, enabling it to be
|
||||
opened by an external IndexReader. This can greatly slow down indexing
|
||||
speed. NOTE: Despite the name, this value does not have any relation to
|
||||
Solr's autoCommit functionality
|
||||
-->
|
||||
<!--<luceneAutoCommit>false</luceneAutoCommit>-->
|
||||
<!--
|
||||
Expert: The Merge Policy in Lucene controls how merging is handled by
|
||||
Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
|
||||
versions used LogDocMergePolicy.
|
||||
|
||||
LogByteSizeMergePolicy chooses segments to merge based on their size. The
|
||||
Lucene 2.2 default, LogDocMergePolicy chose when to merge based on number
|
||||
of documents
|
||||
|
||||
Other implementations of MergePolicy must have a no-argument constructor
|
||||
-->
|
||||
<!--<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy"/>-->
|
||||
<!--
|
||||
Expert:
|
||||
The Merge Scheduler in Lucene controls how merges are performed. The
|
||||
ConcurrentMergeScheduler (Lucene 2.3 default) can perform merges in the
|
||||
background using separate threads. The SerialMergeScheduler (Lucene 2.2
|
||||
default) does not.
|
||||
-->
|
||||
<!--<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>-->
|
||||
<!--
|
||||
This option specifies which Lucene LockFactory implementation to use.
|
||||
|
||||
single = SingleInstanceLockFactory - suggested for a read-only index
|
||||
or when there is no possibility of another process trying
|
||||
to modify the index.
|
||||
native = NativeFSLockFactory - uses OS native file locking
|
||||
simple = SimpleFSLockFactory - uses a plain file for locking
|
||||
|
||||
(For backwards compatibility with Solr 1.2, 'simple' is the default
|
||||
if not specified.)
|
||||
-->
|
||||
<lockType>native</lockType>
|
||||
<!--
|
||||
Expert:
|
||||
Controls how often Lucene loads terms into memory -->
|
||||
<!--<termIndexInterval>256</termIndexInterval>-->
|
||||
</indexDefaults>
|
||||
<mainIndex>
|
||||
<!-- options specific to the main on-disk lucene index -->
|
||||
<useCompoundFile>false</useCompoundFile>
|
||||
<ramBufferSizeMB>32</ramBufferSizeMB>
|
||||
<mergeFactor>10</mergeFactor>
|
||||
<!-- Deprecated -->
|
||||
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
|
||||
<!--<maxMergeDocs>2147483647</maxMergeDocs>-->
|
||||
<!-- inherit from indexDefaults <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.
|
||||
This is not needed if lock type is 'none' or 'single'
|
||||
-->
|
||||
<unlockOnStartup>false</unlockOnStartup>
|
||||
<!-- If true, IndexReaders will be reopened (often more efficient) instead
|
||||
of closed and then opened. -->
|
||||
<reopenReaders>true</reopenReaders>
|
||||
<!--
|
||||
Expert:
|
||||
Controls how often Lucene loads terms into memory. Default is 128 and is likely good for most everyone. -->
|
||||
<!--<termIndexInterval>256</termIndexInterval>-->
|
||||
<!--
|
||||
Custom deletion policies can specified here. The class must
|
||||
implement org.apache.lucene.index.IndexDeletionPolicy.
|
||||
|
||||
http://lucene.apache.org/java/2_3_2/api/org/apache/lucene/index/IndexDeletionPolicy.html
|
||||
|
||||
The standard Solr IndexDeletionPolicy implementation supports deleting
|
||||
index commit points on number of commits, age of commit point and
|
||||
optimized status.
|
||||
|
||||
The latest commit point should always be preserved regardless
|
||||
of the criteria.
|
||||
-->
|
||||
<deletionPolicy class="solr.SolrDeletionPolicy">
|
||||
<!-- The number of commit points to be kept -->
|
||||
<str name="maxCommitsToKeep">1</str>
|
||||
<!-- The number of optimized commit points to be kept -->
|
||||
<str name="maxOptimizedCommitsToKeep">0</str>
|
||||
<!--
|
||||
Delete all commit points once they have reached the given age.
|
||||
Supports DateMathParser syntax e.g.
|
||||
|
||||
<str name="maxCommitAge">30MINUTES</str>
|
||||
<str name="maxCommitAge">1DAY</str>
|
||||
-->
|
||||
</deletionPolicy>
|
||||
<!-- To aid in advanced debugging, you may turn on IndexWriter debug logging.
|
||||
Setting to true will set the file that the underlying Lucene IndexWriter
|
||||
will write its debug infostream to. -->
|
||||
<infoStream file="INFOSTREAM.txt">false</infoStream>
|
||||
</mainIndex>
|
||||
<!-- Enables JMX if and only if an existing MBeanServer is found, use this
|
||||
if you want to configure JMX through JVM parameters. Remove this to disable
|
||||
exposing Solr configuration and statistics to JMX.
|
||||
|
||||
If you want to connect to a particular server, specify the agentId
|
||||
e.g. <jmx agentId="myAgent" />
|
||||
|
||||
If you want to start a new MBeanServer, specify the serviceUrl
|
||||
e.g <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
|
||||
|
||||
For more details see http://wiki.apache.org/solr/SolrJmx
|
||||
-->
|
||||
<jmx/>
|
||||
<!-- 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)
|
||||
-->
|
||||
<!-- Perform a <commit/> automatically under certain conditions:
|
||||
maxDocs - number of updates since last commit is greater than this
|
||||
maxTime - oldest uncommited update (in ms) is this long ago
|
||||
Instead of enabling autoCommit, consider using "commitWithin"
|
||||
when adding documents. http://wiki.apache.org/solr/UpdateXmlMessages
|
||||
<autoCommit>
|
||||
<maxDocs>10000</maxDocs>
|
||||
<maxTime>1000</maxTime>
|
||||
</autoCommit>
|
||||
-->
|
||||
<!-- The RunExecutableListener executes an external command from a
|
||||
hook such as postCommit or postOptimize.
|
||||
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">solr/bin/snapshooter</str>
|
||||
<str name="dir">.</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
|
||||
<listener event="postOptimize" class="solr.RunExecutableListener">
|
||||
<str name="exe">snapshooter</str>
|
||||
<str name="dir">solr/bin</str>
|
||||
<bool name="wait">true</bool>
|
||||
</listener>
|
||||
-->
|
||||
</updateHandler>
|
||||
<!-- Use the following format to specify a custom IndexReaderFactory - allows for alternate
|
||||
IndexReader implementations.
|
||||
|
||||
** Experimental Feature **
|
||||
Please note - Using a custom IndexReaderFactory may prevent certain other features
|
||||
from working. The API to IndexReaderFactory may change without warning or may even
|
||||
be removed from future releases if the problems cannot be resolved.
|
||||
|
||||
** Features that may not work with custom IndexReaderFactory **
|
||||
The ReplicationHandler assumes a disk-resident index. Using a custom
|
||||
IndexReader implementation may cause incompatibility with ReplicationHandler and
|
||||
may cause replication to not work correctly. See SOLR-1366 for details.
|
||||
|
||||
<indexReaderFactory name="IndexReaderFactory" class="package.class">
|
||||
Parameters as required by the implementation
|
||||
</indexReaderFactory >
|
||||
-->
|
||||
<!-- To set the termInfosIndexDivisor, do this: -->
|
||||
<!--<indexReaderFactory name="IndexReaderFactory" class="org.apache.solr.core.StandardIndexReaderFactory">
|
||||
<int name="termInfosIndexDivisor">12</int>
|
||||
</indexReaderFactory >-->
|
||||
<query>
|
||||
<!-- Maximum number of clauses in a boolean query... in the past, this affected
|
||||
range or prefix queries that expanded to big boolean queries - built in Solr
|
||||
query parsers no longer create queries with this limitation.
|
||||
An exception is thrown if exceeded. -->
|
||||
<maxBooleanClauses>1024</maxBooleanClauses>
|
||||
<!-- There are two implementations of cache available for Solr,
|
||||
LRUCache, based on a synchronized LinkedHashMap, and
|
||||
FastLRUCache, based on a ConcurrentHashMap. FastLRUCache has faster gets
|
||||
and slower puts in single threaded operation and thus is generally faster
|
||||
than LRUCache when the hit ratio of the cache is high (> 75%), and may be
|
||||
faster under other scenarios on multi-cpu systems. -->
|
||||
<!-- 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 LRUCache or FastLRUCache
|
||||
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.FastLRUCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
<!-- Cache used to hold field values that are quickly accessible
|
||||
by document id. The fieldValueCache is created by default
|
||||
even if not configured here.
|
||||
<fieldValueCache
|
||||
class="solr.FastLRUCache"
|
||||
size="512"
|
||||
autowarmCount="128"
|
||||
showItems="32"
|
||||
/>
|
||||
-->
|
||||
<!-- 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="0"/>
|
||||
<!-- 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 49 will be collected and cached. Any further
|
||||
requests in that range can be satisfied via the cache. -->
|
||||
<queryResultWindowSize>20</queryResultWindowSize>
|
||||
<!-- Maximum number of documents to cache for any entry in the
|
||||
queryResultCache. -->
|
||||
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
|
||||
<!-- a newSearcher event is fired whenever a new searcher is being prepared
|
||||
and there is a current searcher handling requests (aka registered).
|
||||
It can be used to prime certain caches to prevent long request times for
|
||||
certain requests.
|
||||
-->
|
||||
<!-- 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>
|
||||
<lst><str name="q">static newSearcher warming query from solrconfig.xml</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">solr rocks</str>
|
||||
<str name="start">0</str>
|
||||
<str name="rows">10</str>
|
||||
</lst>
|
||||
<lst>
|
||||
<str name="q">static firstSearcher warming query from solrconfig.xml</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>2</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="true" multipartUploadLimitInKB="2048000"/>
|
||||
<!-- Set HTTP caching related parameters (for proxy caches and clients).
|
||||
|
||||
To get the behaviour of Solr 1.2 (ie: no caching related headers)
|
||||
use the never304="true" option and do not specify a value for
|
||||
<cacheControl>
|
||||
-->
|
||||
<!-- <httpCaching never304="true"> -->
|
||||
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr">
|
||||
<!-- lastModFrom="openTime" is the default, the Last-Modified value
|
||||
(and validation against If-Modified-Since requests) will all be
|
||||
relative to when the current Searcher was opened.
|
||||
You can change it to lastModFrom="dirLastMod" if you want the
|
||||
value to exactly corrispond to when the physical index was last
|
||||
modified.
|
||||
|
||||
etagSeed="..." is an option you can change to force the ETag
|
||||
header (and validation against If-None-Match requests) to be
|
||||
differnet even if the index has not changed (ie: when making
|
||||
significant changes to your config file)
|
||||
|
||||
lastModifiedFrom and etagSeed are both ignored if you use the
|
||||
never304="true" option.
|
||||
-->
|
||||
<!-- If you include a <cacheControl> directive, it will be used to
|
||||
generate a Cache-Control header, as well as an Expires header
|
||||
if the value contains "max-age="
|
||||
|
||||
By default, no Cache-Control header is generated.
|
||||
|
||||
You can use the <cacheControl> option even if you have set
|
||||
never304="true"
|
||||
-->
|
||||
<!-- <cacheControl>max-age=30, public</cacheControl> -->
|
||||
</httpCaching>
|
||||
</requestDispatcher>
|
||||
<!-- requestHandler plugins... incoming queries will be dispatched to the
|
||||
correct handler based on the path or the qt (query type) param.
|
||||
Names starting with a '/' are accessed with the a path equal to the
|
||||
registered name. Names without a leading '/' are accessed with:
|
||||
http://host/app/select?qt=name
|
||||
If no qt is defined, the requestHandler that declares default="true"
|
||||
will be used.
|
||||
-->
|
||||
<requestHandler name="standard" class="solr.SearchHandler" default="true">
|
||||
<!-- 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>
|
||||
<!-- Please refer to http://wiki.apache.org/solr/SolrReplication for details on configuring replication -->
|
||||
<!-- remove the <lst name="master"> section if this is just a slave -->
|
||||
<!-- remove the <lst name="slave"> section if this is just a master -->
|
||||
<!--
|
||||
<requestHandler name="/replication" class="solr.ReplicationHandler" >
|
||||
<lst name="master">
|
||||
<str name="replicateAfter">commit</str>
|
||||
<str name="replicateAfter">startup</str>
|
||||
<str name="confFiles">schema.xml,stopwords.txt</str>
|
||||
</lst>
|
||||
<lst name="slave">
|
||||
<str name="masterUrl">http://localhost:8983/solr/replication</str>
|
||||
<str name="pollInterval">00:00:60</str>
|
||||
</lst>
|
||||
</requestHandler>-->
|
||||
<!-- DisMaxRequestHandler allows easy searching across multiple fields
|
||||
for simple user-entered phrases. It's implementation is now
|
||||
just the standard SearchHandler with a default query type
|
||||
of "dismax".
|
||||
see http://wiki.apache.org/solr/DisMaxRequestHandler
|
||||
-->
|
||||
<requestHandler name="dismax" class="solr.SearchHandler">
|
||||
<lst name="defaults">
|
||||
<str name="defType">dismax</str>
|
||||
<str name="echoParams">explicit</str>
|
||||
<float name="tie">0.01</float>
|
||||
<str name="qf">
|
||||
text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
|
||||
</str>
|
||||
<str name="pf">
|
||||
text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9
|
||||
</str>
|
||||
<str name="bf">
|
||||
popularity^0.5 recip(price,1,1000,1000)^0.3
|
||||
</str>
|
||||
<str name="fl">
|
||||
id,name,price,score
|
||||
</str>
|
||||
<str name="mm">
|
||||
2<-1 5<-2 6<90%
|
||||
</str>
|
||||
<int name="ps">100</int>
|
||||
<str name="q.alt">*:*</str>
|
||||
<!-- example highlighter config, enable per-query with hl=true -->
|
||||
<str name="hl.fl">text features name</str>
|
||||
<!-- for this field, we want no fragmenting, just highlighting -->
|
||||
<str name="f.name.hl.fragsize">0</str>
|
||||
<!-- instructs Solr to return the field itself if no query terms are
|
||||
found -->
|
||||
<str name="f.name.hl.alternateField">name</str>
|
||||
<str name="f.text.hl.fragmenter">regex</str>
|
||||
<!-- defined below -->
|
||||
</lst>
|
||||
</requestHandler>
|
||||
<!-- Note how you can register the same handler multiple times with
|
||||
different names (and different init parameters)
|
||||
-->
|
||||
<requestHandler name="partitioned" class="solr.SearchHandler">
|
||||
<lst name="defaults">
|
||||
<str name="defType">dismax</str>
|
||||
<str name="echoParams">explicit</str>
|
||||
<str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str>
|
||||
<str name="mm">2<-1 5<-2 6<90%</str>
|
||||
<!-- This is an example of using Date Math to specify a constantly
|
||||
moving date range in a config...
|
||||
-->
|
||||
<str name="bq">incubationdate_dt:[* TO NOW/DAY-1MONTH]^2.2</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">
|
||||
<str name="fq">inStock:true</str>
|
||||
</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.field">cat</str>
|
||||
<str name="facet.field">manu_exact</str>
|
||||
<str name="facet.query">price:[* TO 500]</str>
|
||||
<str name="facet.query">price:[500 TO *]</str>
|
||||
</lst>
|
||||
</requestHandler>
|
||||
|
||||
<searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
|
||||
|
||||
<searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" />
|
||||
<!--
|
||||
Search components are registered to SolrCore and used by Search Handlers
|
||||
|
||||
By default, the following components are avaliable:
|
||||
|
||||
<searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
|
||||
<searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" />
|
||||
<searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" />
|
||||
<searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
|
||||
<searchComponent name="stats" class="org.apache.solr.handler.component.StatsComponent" />
|
||||
<searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" />
|
||||
|
||||
Default configuration in a requestHandler would look like:
|
||||
<arr name="components">
|
||||
<str>query</str>
|
||||
<str>facet</str>
|
||||
<str>mlt</str>
|
||||
<str>highlight</str>
|
||||
<str>stats</str>
|
||||
<str>debug</str>
|
||||
</arr>
|
||||
|
||||
If you register a searchComponent to one of the standard names, that will be used instead.
|
||||
To insert components before or after the 'standard' components, use:
|
||||
|
||||
<arr name="first-components">
|
||||
<str>myFirstComponentName</str>
|
||||
</arr>
|
||||
|
||||
<arr name="last-components">
|
||||
<str>myLastComponentName</str>
|
||||
</arr>
|
||||
-->
|
||||
<!-- The spell check component can return a list of alternative spelling
|
||||
suggestions. -->
|
||||
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
|
||||
<str name="queryAnalyzerFieldType">textSpell</str>
|
||||
<lst name="spellchecker">
|
||||
<str name="name">default</str>
|
||||
<str name="field">name</str>
|
||||
<str name="spellcheckIndexDir">./spellchecker</str>
|
||||
</lst>
|
||||
<!-- a spellchecker that uses a different distance measure
|
||||
<lst name="spellchecker">
|
||||
<str name="name">jarowinkler</str>
|
||||
<str name="field">spell</str>
|
||||
<str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
|
||||
<str name="spellcheckIndexDir">./spellchecker2</str>
|
||||
</lst>
|
||||
-->
|
||||
<!-- a file based spell checker
|
||||
<lst name="spellchecker">
|
||||
<str name="classname">solr.FileBasedSpellChecker</str>
|
||||
<str name="name">file</str>
|
||||
<str name="sourceLocation">spellings.txt</str>
|
||||
<str name="characterEncoding">UTF-8</str>
|
||||
<str name="spellcheckIndexDir">./spellcheckerFile</str>
|
||||
</lst>
|
||||
-->
|
||||
</searchComponent>
|
||||
<!-- A request handler utilizing the spellcheck component.
|
||||
#############################################################################
|
||||
NOTE: This is purely as an example. The whole purpose of the
|
||||
SpellCheckComponent is to hook it into the request handler that handles (i.e.
|
||||
the standard or dismax SearchHandler) queries such that a separate request is
|
||||
not needed to get suggestions.
|
||||
|
||||
IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS NOT WHAT YOU
|
||||
WANT FOR YOUR PRODUCTION SYSTEM!
|
||||
#############################################################################
|
||||
-->
|
||||
<requestHandler name="/spell" class="solr.SearchHandler" lazy="true">
|
||||
<lst name="defaults">
|
||||
<!-- omp = Only More Popular -->
|
||||
<str name="spellcheck.onlyMorePopular">false</str>
|
||||
<!-- exr = Extended Results -->
|
||||
<str name="spellcheck.extendedResults">false</str>
|
||||
<!-- The number of suggestions to return -->
|
||||
<str name="spellcheck.count">1</str>
|
||||
</lst>
|
||||
<arr name="last-components">
|
||||
<str>spellcheck</str>
|
||||
</arr>
|
||||
</requestHandler>
|
||||
<searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
|
||||
<!-- A Req Handler for working with the tvComponent. This is purely as an example.
|
||||
You will likely want to add the component to your already specified request handlers. -->
|
||||
<requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
|
||||
<lst name="defaults">
|
||||
<bool name="tv">true</bool>
|
||||
</lst>
|
||||
<arr name="last-components">
|
||||
<str>tvComponent</str>
|
||||
</arr>
|
||||
</requestHandler>
|
||||
<!-- Clustering Component
|
||||
http://wiki.apache.org/solr/ClusteringComponent
|
||||
This relies on third party jars which are not included in the release.
|
||||
To use this component (and the "/clustering" handler)
|
||||
Those jars will need to be downloaded, and you'll need to set the
|
||||
solr.cluster.enabled system property when running solr...
|
||||
java -Dsolr.clustering.enabled=true -jar start.jar
|
||||
-->
|
||||
<searchComponent name="clusteringComponent" enable="${solr.clustering.enabled:false}" class="org.apache.solr.handler.clustering.ClusteringComponent">
|
||||
<!-- Declare an engine -->
|
||||
<lst name="engine">
|
||||
<!-- The name, only one can be named "default" -->
|
||||
<str name="name">default</str>
|
||||
<!--
|
||||
Class name of Carrot2 clustering algorithm. Currently available algorithms are:
|
||||
|
||||
* org.carrot2.clustering.lingo.LingoClusteringAlgorithm
|
||||
* org.carrot2.clustering.stc.STCClusteringAlgorithm
|
||||
|
||||
See http://project.carrot2.org/algorithms.html for the algorithm's characteristics.
|
||||
-->
|
||||
<str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
|
||||
<!--
|
||||
Overriding values for Carrot2 default algorithm attributes. For a description
|
||||
of all available attributes, see: http://download.carrot2.org/stable/manual/#chapter.components.
|
||||
Use attribute key as name attribute of str elements below. These can be further
|
||||
overridden for individual requests by specifying attribute key as request
|
||||
parameter name and attribute value as parameter value.
|
||||
-->
|
||||
<str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
|
||||
</lst>
|
||||
<lst name="engine">
|
||||
<str name="name">stc</str>
|
||||
<str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
|
||||
</lst>
|
||||
</searchComponent>
|
||||
<requestHandler name="/clustering" enable="${solr.clustering.enabled:false}" class="solr.SearchHandler">
|
||||
<lst name="defaults">
|
||||
<bool name="clustering">true</bool>
|
||||
<str name="clustering.engine">default</str>
|
||||
<bool name="clustering.results">true</bool>
|
||||
<!-- The title field -->
|
||||
<str name="carrot.title">name</str>
|
||||
<str name="carrot.url">id</str>
|
||||
<!-- The field to cluster on -->
|
||||
<str name="carrot.snippet">features</str>
|
||||
<!-- produce summaries -->
|
||||
<bool name="carrot.produceSummary">true</bool>
|
||||
<!-- the maximum number of labels per cluster -->
|
||||
<!--<int name="carrot.numDescriptions">5</int>-->
|
||||
<!-- produce sub clusters -->
|
||||
<bool name="carrot.outputSubClusters">false</bool>
|
||||
</lst>
|
||||
<arr name="last-components">
|
||||
<str>clusteringComponent</str>
|
||||
</arr>
|
||||
</requestHandler>
|
||||
<!-- Solr Cell: http://wiki.apache.org/solr/ExtractingRequestHandler -->
|
||||
<requestHandler name="/update/extract" class="org.apache.solr.handler.extraction.ExtractingRequestHandler" startup="lazy">
|
||||
<lst name="defaults">
|
||||
<!-- All the main content goes into "text"... if you need to return
|
||||
the extracted text or do highlighting, use a stored field. -->
|
||||
<str name="fmap.content">text</str>
|
||||
<str name="lowernames">true</str>
|
||||
<str name="uprefix">ignored_</str>
|
||||
<!-- capture link hrefs but ignore div attributes -->
|
||||
<str name="captureAttr">true</str>
|
||||
<str name="fmap.a">links</str>
|
||||
<str name="fmap.div">ignored_</str>
|
||||
</lst>
|
||||
</requestHandler>
|
||||
<!-- A component to return terms and document frequency of those terms.
|
||||
This component does not yet support distributed search. -->
|
||||
<searchComponent name="termsComponent" class="org.apache.solr.handler.component.TermsComponent"/>
|
||||
<requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
|
||||
<lst name="defaults">
|
||||
<bool name="terms">true</bool>
|
||||
</lst>
|
||||
<arr name="components">
|
||||
<str>termsComponent</str>
|
||||
</arr>
|
||||
</requestHandler>
|
||||
<!-- a search component that enables you to configure the top results for
|
||||
a given query regardless of the normal lucene scoring.-->
|
||||
<searchComponent name="elevator" class="solr.QueryElevationComponent">
|
||||
<!-- pick a fieldType to analyze queries -->
|
||||
<str name="queryFieldType">string</str>
|
||||
<str name="config-file">elevate.xml</str>
|
||||
</searchComponent>
|
||||
<!-- a request handler utilizing the elevator component -->
|
||||
<requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
|
||||
<lst name="defaults">
|
||||
<str name="echoParams">explicit</str>
|
||||
</lst>
|
||||
<arr name="last-components">
|
||||
<str>elevator</str>
|
||||
</arr>
|
||||
</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"/>
|
||||
<requestHandler name="/update/javabin" class="solr.BinaryUpdateRequestHandler"/>
|
||||
<!--
|
||||
Analysis request handler. Since Solr 1.3. Use to return how a document is analyzed. Useful
|
||||
for debugging and as a token server for other types of applications.
|
||||
|
||||
This is deprecated in favor of the improved DocumentAnalysisRequestHandler and FieldAnalysisRequestHandler
|
||||
|
||||
<requestHandler name="/analysis" class="solr.AnalysisRequestHandler" />
|
||||
-->
|
||||
<!--
|
||||
An analysis handler that provides a breakdown of the analysis process of provided docuemnts. This handler expects a
|
||||
(single) content stream with the following format:
|
||||
|
||||
<docs>
|
||||
<doc>
|
||||
<field name="id">1</field>
|
||||
<field name="name">The Name</field>
|
||||
<field name="text">The Text Value</field>
|
||||
<doc>
|
||||
<doc>...</doc>
|
||||
<doc>...</doc>
|
||||
...
|
||||
</docs>
|
||||
|
||||
Note: Each document must contain a field which serves as the unique key. This key is used in the returned
|
||||
response to assoicate an analysis breakdown to the analyzed document.
|
||||
|
||||
Like the FieldAnalysisRequestHandler, this handler also supports query analysis by
|
||||
sending either an "analysis.query" or "q" request paraemter that holds the query text to be analyized. It also
|
||||
supports the "analysis.showmatch" parameter which when set to true, all field tokens that match the query
|
||||
tokens will be marked as a "match".
|
||||
-->
|
||||
<requestHandler name="/analysis/document" class="solr.DocumentAnalysisRequestHandler"/>
|
||||
<!--
|
||||
RequestHandler that provides much the same functionality as analysis.jsp. Provides the ability
|
||||
to specify multiple field types and field names in the same request and outputs index-time and
|
||||
query-time analysis for each of them.
|
||||
|
||||
Request parameters are:
|
||||
analysis.fieldname - The field name whose analyzers are to be used
|
||||
analysis.fieldtype - The field type whose analyzers are to be used
|
||||
analysis.fieldvalue - The text for index-time analysis
|
||||
q (or analysis.q) - The text for query time analysis
|
||||
analysis.showmatch (true|false) - When set to true and when query analysis is performed, the produced
|
||||
tokens of the field value analysis will be marked as "matched" for every
|
||||
token that is produces by the query analysis
|
||||
-->
|
||||
<requestHandler name="/analysis/field" class="solr.FieldAnalysisRequestHandler"/>
|
||||
<!-- CSV update handler, loaded on demand -->
|
||||
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy"/>
|
||||
<!--
|
||||
Admin Handlers - This will register all the standard admin RequestHandlers. Adding
|
||||
this single handler is equivalent to registering:
|
||||
|
||||
<requestHandler name="/admin/luke" class="org.apache.solr.handler.admin.LukeRequestHandler" />
|
||||
<requestHandler name="/admin/system" class="org.apache.solr.handler.admin.SystemInfoHandler" />
|
||||
<requestHandler name="/admin/plugins" class="org.apache.solr.handler.admin.PluginInfoHandler" />
|
||||
<requestHandler name="/admin/threads" class="org.apache.solr.handler.admin.ThreadDumpHandler" />
|
||||
<requestHandler name="/admin/properties" class="org.apache.solr.handler.admin.PropertiesRequestHandler" />
|
||||
<requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
|
||||
|
||||
If you wish to hide files under ${solr.home}/conf, explicitly register the ShowFileRequestHandler using:
|
||||
<requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
|
||||
<lst name="invariants">
|
||||
<str name="hidden">synonyms.txt</str>
|
||||
<str name="hidden">anotherfile.txt</str>
|
||||
</lst>
|
||||
</requestHandler>
|
||||
-->
|
||||
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers"/>
|
||||
<!-- ping/healthcheck -->
|
||||
<requestHandler name="/admin/ping" class="PingRequestHandler">
|
||||
<lst name="defaults">
|
||||
<str name="qt">standard</str>
|
||||
<str name="q">solrpingquery</str>
|
||||
<str name="echoParams">all</str>
|
||||
</lst>
|
||||
</requestHandler>
|
||||
<!-- 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>
|
||||
<highlighting>
|
||||
<!-- Configure the standard fragmenter -->
|
||||
<!-- This could most likely be commented out in the "default" case -->
|
||||
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
|
||||
<lst name="defaults">
|
||||
<int name="hl.fragsize">100</int>
|
||||
</lst>
|
||||
</fragmenter>
|
||||
<!-- A regular-expression-based fragmenter (f.i., for sentence extraction) -->
|
||||
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
|
||||
<lst name="defaults">
|
||||
<!-- slightly smaller fragsizes work better because of slop -->
|
||||
<int name="hl.fragsize">70</int>
|
||||
<!-- allow 50% slop on fragment sizes -->
|
||||
<float name="hl.regex.slop">0.5</float>
|
||||
<!-- a basic sentence pattern -->
|
||||
<str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
|
||||
</lst>
|
||||
</fragmenter>
|
||||
<!-- Configure the standard formatter -->
|
||||
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
|
||||
<lst name="defaults">
|
||||
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
|
||||
<str name="hl.simple.post"><![CDATA[</em>]]></str>
|
||||
</lst>
|
||||
</formatter>
|
||||
</highlighting>
|
||||
<!-- An example dedup update processor that creates the "id" field on the fly
|
||||
based on the hash code of some other fields. This example has overwriteDupes
|
||||
set to false since we are using the id field as the signatureField and Solr
|
||||
will maintain uniqueness based on that anyway.
|
||||
|
||||
You have to link the chain to an update handler above to use it ie:
|
||||
<requestHandler name="/update "class="solr.XmlUpdateRequestHandler">
|
||||
<lst name="defaults">
|
||||
<str name="update.processor">dedupe</str>
|
||||
</lst>
|
||||
</requestHandler>
|
||||
-->
|
||||
<!--
|
||||
<updateRequestProcessorChain name="dedupe">
|
||||
<processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
|
||||
<bool name="enabled">true</bool>
|
||||
<str name="signatureField">id</str>
|
||||
<bool name="overwriteDupes">false</bool>
|
||||
<str name="fields">name,features,cat</str>
|
||||
<str name="signatureClass">org.apache.solr.update.processor.Lookup3Signature</str>
|
||||
</processor>
|
||||
<processor class="solr.LogUpdateProcessorFactory" />
|
||||
<processor class="solr.RunUpdateProcessorFactory" />
|
||||
</updateRequestProcessorChain>
|
||||
-->
|
||||
<!-- queryResponseWriter plugins... query responses will be written using the
|
||||
writer specified by the 'wt' request parameter matching the name of a registered
|
||||
writer.
|
||||
The "default" 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="xml" class="org.apache.solr.request.XMLResponseWriter" default="true"/>
|
||||
<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="php" class="org.apache.solr.request.PHPResponseWriter"/>
|
||||
<queryResponseWriter name="phps" class="org.apache.solr.request.PHPSerializedResponseWriter"/>
|
||||
|
||||
<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>
|
||||
<!-- example of registering a query parser
|
||||
<queryParser name="lucene" class="org.apache.solr.search.LuceneQParserPlugin"/>
|
||||
-->
|
||||
<!-- example of registering a custom function parser
|
||||
<valueSourceParser name="myfunc" class="com.mycompany.MyValueSourceParser" />
|
||||
-->
|
||||
<!-- 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>
|
||||
<requestHandler class="solr.MoreLikeThisHandler" name="/mlt">
|
||||
<lst name="defaults">
|
||||
<str name="mlt.mintf">1</str>
|
||||
<str name="mlt.mindf">2</str>
|
||||
</lst>
|
||||
</requestHandler>
|
||||
</config>
|
|
@ -1,2 +0,0 @@
|
|||
pizza
|
||||
history
|
|
@ -1,58 +0,0 @@
|
|||
# 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.
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# a couple of test stopwords to test that the words are really being
|
||||
# configured from this file:
|
||||
stopworda
|
||||
stopwordb
|
||||
|
||||
#Standard english stop words taken from Lucene's StopAnalyzer
|
||||
a
|
||||
an
|
||||
and
|
||||
are
|
||||
as
|
||||
at
|
||||
be
|
||||
but
|
||||
by
|
||||
for
|
||||
if
|
||||
in
|
||||
into
|
||||
is
|
||||
it
|
||||
no
|
||||
not
|
||||
of
|
||||
on
|
||||
or
|
||||
s
|
||||
such
|
||||
t
|
||||
that
|
||||
the
|
||||
their
|
||||
then
|
||||
there
|
||||
these
|
||||
they
|
||||
this
|
||||
to
|
||||
was
|
||||
will
|
||||
with
|
||||
|
|
@ -1,31 +0,0 @@
|
|||
# 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
|
||||
|
|
@ -0,0 +1,885 @@
|
|||
# encoding: UTF-8
|
||||
#
|
||||
# **Tire** provides rich and comfortable Ruby API for the
|
||||
# [_ElasticSearch_](http://www.elasticsearch.org/) search engine/database.
|
||||
#
|
||||
# _ElasticSearch_ is a scalable, distributed, cloud-ready, highly-available
|
||||
# full-text search engine and database, communicating by JSON over RESTful HTTP,
|
||||
# based on [Lucene](http://lucene.apache.org/), written in Java.
|
||||
#
|
||||
# <img src="http://github.com/favicon.ico" style="position:relative; top:2px">
|
||||
# _Tire_ is open source, and you can download or clone the source code
|
||||
# from <https://github.com/karmi/tire>.
|
||||
#
|
||||
# By following these instructions you should have the search running
|
||||
# on a sane operation system in less then 10 minutes.
|
||||
|
||||
# Note, that this file can be executed directly:
|
||||
#
|
||||
# ruby -I lib examples/tire-dsl.rb
|
||||
#
|
||||
|
||||
|
||||
#### Installation
|
||||
|
||||
# Install _Tire_ with _Rubygems_:
|
||||
|
||||
#
|
||||
# gem install tire
|
||||
#
|
||||
require 'rubygems'
|
||||
require 'colorize'
|
||||
|
||||
# _Tire_ uses the [_multi_json_](https://github.com/intridea/multi_json) gem as a generic JSON library.
|
||||
# We want to use the [_yajl-ruby_](https://github.com/brianmario/yajl-ruby) gem in its full on mode here.
|
||||
#
|
||||
require 'yajl/json_gem'
|
||||
|
||||
# Now, let's require the _Tire_ gem itself, and we're ready to go.
|
||||
#
|
||||
require 'tire'
|
||||
|
||||
#### Prerequisites
|
||||
|
||||
# We'll need a working and running _ElasticSearch_ server, of course. Thankfully, that's easy.
|
||||
( puts <<-"INSTALL" ; exit(1) ) unless (RestClient.get('http://localhost:9200') rescue false)
|
||||
|
||||
[ERROR] You don’t appear to have ElasticSearch installed. Please install and launch it with the following commands:
|
||||
|
||||
curl -k -L -o elasticsearch-0.19.0.tar.gz http://github.com/downloads/elasticsearch/elasticsearch/elasticsearch-0.19.0.tar.gz
|
||||
tar -zxvf elasticsearch-0.19.0.tar.gz
|
||||
./elasticsearch-0.19.0/bin/elasticsearch -f
|
||||
INSTALL
|
||||
|
||||
### Storing and indexing documents
|
||||
|
||||
# Let's initialize an index named “articles”.
|
||||
#
|
||||
Tire.index 'articles' do
|
||||
# To make sure it's fresh, let's delete any existing index with the same name.
|
||||
#
|
||||
delete
|
||||
# And then, let's create it.
|
||||
#
|
||||
create
|
||||
|
||||
# We want to store and index some articles with `title`, `tags` and `published_on` properties.
|
||||
# Simple Hashes are OK. The default type is „document”.
|
||||
#
|
||||
store :title => '復興「校球」 政大男足決戰UFA足球聯賽', :tags => ['足球'], :published_on => '2011-01-01'
|
||||
store :title => '社科院舉辦碩博士班畢業生撥穗典禮', :tags => ['博士班', '畢業'], :published_on => '2011-01-02'
|
||||
|
||||
# We usually want to set a specific _type_ for the document in _ElasticSearch_.
|
||||
# Simply setting a `type` property is OK.
|
||||
#
|
||||
store :type => 'article',
|
||||
:title => '支持政大學子 羅家倫之女設立獎學金',
|
||||
:tags => ['獎學金'],
|
||||
:published_on => '2011-01-02'
|
||||
|
||||
# We may want to wrap your data in a Ruby class, and use it when storing data.
|
||||
# The contract required of such a class is very simple.
|
||||
#
|
||||
class Article
|
||||
|
||||
#
|
||||
attr_reader :title, :tags, :published_on
|
||||
def initialize(attributes={})
|
||||
@attributes = attributes
|
||||
@attributes.each_pair { |name,value| instance_variable_set :"@#{name}", value }
|
||||
end
|
||||
|
||||
# It must provide a `type`, `_type` or `document_type` method for propper mapping.
|
||||
#
|
||||
def type
|
||||
'article'
|
||||
end
|
||||
|
||||
# And it must provide a `to_indexed_json` method for conversion to JSON.
|
||||
#
|
||||
def to_indexed_json
|
||||
@attributes.to_json
|
||||
end
|
||||
end
|
||||
|
||||
# Note: Since our class takes a Hash of attributes on initialization, we may even
|
||||
# wrap the results in instances of this class; we'll see how to do that further below.
|
||||
#
|
||||
article = Article.new :title => '親身感受臺灣特色 日本田野研究團政大學習',
|
||||
:tags => ['臺灣特色', '日本'],
|
||||
:published_on => '2011-01-03'
|
||||
|
||||
# Let's store the `article`, now.
|
||||
#
|
||||
store article
|
||||
|
||||
# And let's „force refresh“ the index, so we can query it immediately.
|
||||
#
|
||||
refresh
|
||||
end
|
||||
|
||||
# We may want to define a specific [mapping](http://www.elasticsearch.org/guide/reference/api/admin-indices-create-index.html)
|
||||
# for the index.
|
||||
|
||||
Tire.index 'articles' do
|
||||
# To do so, let's just pass a Hash containing the specified mapping to the `Index#create` method.
|
||||
#
|
||||
create :mappings => {
|
||||
|
||||
# Let's specify for which _type_ of documents this mapping should be used:
|
||||
# „article”, in our case.
|
||||
#
|
||||
:article => {
|
||||
:properties => {
|
||||
|
||||
# Let's specify the type of the field, whether it should be analyzed, ...
|
||||
#
|
||||
:id => { :type => 'string', :index => 'not_analyzed', :include_in_all => false },
|
||||
|
||||
# ... set the boost or analyzer settings for the field, etc. The _ElasticSearch_ guide
|
||||
# has [more information](http://elasticsearch.org/guide/reference/mapping/index.html).
|
||||
# Don't forget, that proper mapping is key to efficient and effective search.
|
||||
# But don't fret about getting the mapping right the first time, you won't.
|
||||
# In most cases, the default, dynamic mapping is just fine for prototyping.
|
||||
#
|
||||
:title => { :type => 'string', :analyzer => 'cjk', :boost => 2.0 },
|
||||
:tags => { :type => 'string', :analyzer => 'keyword' },
|
||||
:content => { :type => 'string', :analyzer => 'cjk' }
|
||||
}
|
||||
}
|
||||
}
|
||||
end
|
||||
|
||||
#### Bulk Indexing
|
||||
|
||||
# Of course, we may have large amounts of data, and adding them to the index one by one really isn't the best idea.
|
||||
# We can use _ElasticSearch's_ [bulk API](http://www.elasticsearch.org/guide/reference/api/bulk.html)
|
||||
# for importing the data.
|
||||
|
||||
# So, for demonstration purposes, let's suppose we have a simple collection of hashes to store.
|
||||
#
|
||||
articles = [
|
||||
|
||||
# Notice that such objects must have an `id` property!
|
||||
#
|
||||
{ :id => '1', :type => 'article', :title => '復興「校球」 政大男足決戰UFA足球聯賽', :tags => ['足球'], :published_on => '2011-01-01' },
|
||||
|
||||
# And, of course, they should contain the `type` property for the mapping to work!
|
||||
#
|
||||
{ :id => '2', :type => 'article', :title => '社科院舉辦碩博士班畢業生撥穗典禮', :tags => ['博士班', '畢業','社科院'], :published_on => '2011-01-02' },
|
||||
{ :id => '3', :type => 'article', :title => '支持政大學子 羅家倫之女設立獎學金', :tags => ['獎學金'], :published_on => '2011-01-02' },
|
||||
{ :id => '4', :type => 'article', :title => '親身感受臺灣特色 日本田野研究團政大學習', :tags => ['臺灣特色', '日本'], :published_on => '2011-01-03' }
|
||||
]
|
||||
|
||||
# We can just push them into the index in one go.
|
||||
#
|
||||
Tire.index 'articles' do
|
||||
import articles
|
||||
end
|
||||
|
||||
# Of course, we can easily manipulate the documents before storing them in the index.
|
||||
#
|
||||
Tire.index 'articles' do
|
||||
delete
|
||||
|
||||
# ... by passing a block to the `import` method. The collection will
|
||||
# be available in the block argument.
|
||||
#
|
||||
import articles do |documents|
|
||||
|
||||
# We will capitalize every _title_ and return the manipulated collection
|
||||
# back to the `import` method.
|
||||
#
|
||||
documents.map { |document| document.update(:title => document[:title].capitalize) }
|
||||
end
|
||||
|
||||
refresh
|
||||
end
|
||||
|
||||
### Searching
|
||||
|
||||
# With the documents indexed and stored in the _ElasticSearch_ database, we can search them, finally.
|
||||
#
|
||||
# _Tire_ exposes the search interface via simple domain-specific language.
|
||||
|
||||
#### Simple Query String Searches
|
||||
|
||||
# We can do simple searches, like searching for articles containing “One” in their title.
|
||||
#
|
||||
s = Tire.search('news_bulletins') do
|
||||
query do
|
||||
string "title:政大"
|
||||
end
|
||||
end
|
||||
|
||||
# The results:
|
||||
# * One [tags: ruby]
|
||||
#
|
||||
s.results.each do |document|
|
||||
puts "Test1==============================Has results: #{s.results.count}".yellow
|
||||
puts "* #{ document.title } [tags: ]"
|
||||
end
|
||||
|
||||
# Or, we can search for articles published between January, 1st and January, 2nd.
|
||||
#
|
||||
puts "Test2==Or, we can search for articles published between January, 1st and January, 2nd.=Has results: #{s.results.count}".yellow
|
||||
s = Tire.search('articles') do
|
||||
query do
|
||||
string "published_on:[2011-01-01 TO 2011-01-02]"
|
||||
end
|
||||
end
|
||||
|
||||
# The results:
|
||||
# * One [published: 2011-01-01]
|
||||
# * Two [published: 2011-01-02]
|
||||
# * Three [published: 2011-01-02]
|
||||
#
|
||||
s.results.each do |document|
|
||||
puts "* #{ document.title } [published: #{document.published_on}]"
|
||||
end
|
||||
|
||||
# Notice, that we can access local variables from the _enclosing scope_.
|
||||
# (Of course, we may write the blocks in shorter notation.)
|
||||
|
||||
# We will define the query in a local variable named `q`...
|
||||
#
|
||||
q = "title:T*"
|
||||
# ... and we can use it inside the `query` block.
|
||||
#
|
||||
s = Tire.search('articles') { query { string q } }
|
||||
|
||||
# The results:
|
||||
# * Two [tags: ruby, python]
|
||||
# * Three [tags: java]
|
||||
#
|
||||
puts "Test3==and we can use it inside the `query` block..[ #{q} ]=Has results: #{s.results.count}".yellow
|
||||
s.results.each do |document|
|
||||
puts "* #{ document.title } [tags:]"
|
||||
end
|
||||
|
||||
# Often, we need to access variables or methods defined in the _outer scope_.
|
||||
# To do that, we have to use a slight variation of the DSL.
|
||||
#
|
||||
|
||||
# Let's assume we have a plain Ruby class, named `Article`.
|
||||
#
|
||||
class Article
|
||||
|
||||
# We will define the query in a class method...
|
||||
#
|
||||
def self.q
|
||||
"title:T*"
|
||||
end
|
||||
|
||||
# ... and wrap the _Tire_ search method in another one.
|
||||
def self.search
|
||||
|
||||
# Notice how we pass the `search` object around as a block argument.
|
||||
#
|
||||
Tire.search('articles') do |search|
|
||||
|
||||
# And we pass the query object in a similar matter.
|
||||
#
|
||||
search.query do |query|
|
||||
|
||||
# Which means we can access the `q` class method.
|
||||
#
|
||||
query.string self.q
|
||||
end
|
||||
end.results
|
||||
end
|
||||
end
|
||||
|
||||
# We may use any valid [Lucene query syntax](http://lucene.apache.org/java/3_0_3/queryparsersyntax.html)
|
||||
# for the `query_string` queries.
|
||||
|
||||
# For debugging our queries, we can display the JSON which is being sent to _ElasticSearch_.
|
||||
#
|
||||
# {"query":{"query_string":{"query":"title:T*"}}}
|
||||
#
|
||||
puts "", "Query:", "-"*80
|
||||
puts s.to_json.green
|
||||
|
||||
# Or better yet, we may display a complete `curl` command to recreate the request in terminal,
|
||||
# so we can see the naked response, tweak request parameters and meditate on problems.
|
||||
#
|
||||
# curl -X POST "http://localhost:9200/articles/_search?pretty=true" \
|
||||
# -d '{"query":{"query_string":{"query":"title:T*"}}}'
|
||||
#
|
||||
puts "", "Try the query in Curl:", "-"*80
|
||||
puts s.to_curl.green
|
||||
|
||||
|
||||
### Logging
|
||||
|
||||
# For debugging more complex situations, we can enable logging, so requests and responses
|
||||
# will be logged using this `curl`-friendly format.
|
||||
|
||||
Tire.configure do
|
||||
|
||||
# By default, at the _info_ level, only the `curl`-format of request and
|
||||
# basic information about the response will be logged:
|
||||
#
|
||||
# # 2011-04-24 11:34:01:150 [CREATE] ("articles")
|
||||
# #
|
||||
# curl -X POST "http://localhost:9200/articles"
|
||||
#
|
||||
# # 2011-04-24 11:34:01:152 [200]
|
||||
#
|
||||
logger 'elasticsearch.log'
|
||||
|
||||
# For debugging, we can switch to the _debug_ level, which will log the complete JSON responses.
|
||||
#
|
||||
# That's very convenient if we want to post a recreation of some problem or solution
|
||||
# to the mailing list, IRC channel, etc.
|
||||
#
|
||||
logger 'elasticsearch.log', :level => 'debug'
|
||||
|
||||
# Note that we can pass any [`IO`](http://www.ruby-doc.org/core/classes/IO.html)-compatible Ruby object as a logging device.
|
||||
#
|
||||
logger STDERR
|
||||
end
|
||||
|
||||
### Configuration
|
||||
|
||||
# As we have just seen with logging, we can configure various parts of _Tire_.
|
||||
#
|
||||
Tire.configure do
|
||||
|
||||
# First of all, we can configure the URL for _ElasticSearch_.
|
||||
#
|
||||
url "http://search.example.com"
|
||||
|
||||
# Second, we may want to wrap the result items in our own class, for instance
|
||||
# the `Article` class set above.
|
||||
#
|
||||
wrapper Article
|
||||
|
||||
# Finally, we can reset one or all configuration settings to their defaults.
|
||||
#
|
||||
reset :url
|
||||
reset
|
||||
|
||||
end
|
||||
|
||||
|
||||
### Complex Searching
|
||||
|
||||
# Query strings are convenient for simple searches, but we may want to define our queries more expressively,
|
||||
# using the _ElasticSearch_ [Query DSL](http://www.elasticsearch.org/guide/reference/query-dsl/index.html).
|
||||
#
|
||||
s = Tire.search('articles') do
|
||||
|
||||
# Let's suppose we want to search for articles with specific _tags_, in our case “ruby” _or_ “python”.
|
||||
#
|
||||
query do
|
||||
|
||||
# That's a great excuse to use a [_terms_](http://elasticsearch.org/guide/reference/query-dsl/terms-query.html)
|
||||
# query.
|
||||
#
|
||||
terms :tags, ['ruby', 'python']
|
||||
end
|
||||
end
|
||||
|
||||
# The search, as expected, returns three articles, all tagged “ruby” — among other tags:
|
||||
#
|
||||
# * Two [tags: ruby, python]
|
||||
# * One [tags: ruby]
|
||||
# * Four [tags: ruby, php]
|
||||
#
|
||||
puts "Test4==The search, as expected, returns three articles, all tagged “STHs” — among other tags.Has results: #{s.results.count}".yellow
|
||||
s.results.each do |document|
|
||||
puts "* #{ document.title } [tags: ]"
|
||||
end
|
||||
|
||||
# What if we wanted to search for articles tagged both “ruby” _and_ “python”?
|
||||
#
|
||||
s = Tire.search('articles') do
|
||||
query do
|
||||
|
||||
# That's a great excuse to specify `minimum_match` for the query.
|
||||
#
|
||||
terms :tags, ['ruby', 'python'], :minimum_match => 2
|
||||
end
|
||||
end
|
||||
|
||||
# The search, as expected, returns one article, tagged with _both_ “ruby” and “python”:
|
||||
#
|
||||
# * Two [tags: ruby, python]
|
||||
#
|
||||
puts "Test5==The search, as expected, returns one article, tagged with _both_ 'ruby' and 'python'.Has results: #{s.results.count}".yellow
|
||||
s.results.each do |document|
|
||||
puts "* #{ document.title } [tags: ]"
|
||||
end
|
||||
|
||||
#### Boolean Queries
|
||||
|
||||
# Quite often, we need complex queries with boolean logic.
|
||||
# Instead of composing long query strings such as `tags:ruby OR tags:java AND NOT tags:python`,
|
||||
# we can use the [_bool_](http://www.elasticsearch.org/guide/reference/query-dsl/bool-query.html)
|
||||
# query.
|
||||
|
||||
s = Tire.search('news_bulletins') do
|
||||
query do
|
||||
|
||||
# In _Tire_, we can build `bool` queries declaratively, as usual.
|
||||
boolean do
|
||||
|
||||
# Let's define a `should` (`OR`) query for _ruby_,
|
||||
#
|
||||
should { string 'title:政大' }
|
||||
|
||||
# as well as for _java_,
|
||||
must_not { string 'title:復興' }
|
||||
|
||||
# while defining a `must_not` (`AND NOT`) query for _python_.
|
||||
# must_not { string 'tags:python' }
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
# The search returns these documents:
|
||||
#
|
||||
# * One [tags: ruby]
|
||||
# * Three [tags: java]
|
||||
# * Four [tags: ruby, php]
|
||||
puts "Test6==Boolean Queries.Has results: #{s.results.count}".yellow
|
||||
s.results.each do |document|
|
||||
puts "* #{ document.title } [tags: ]"
|
||||
end
|
||||
|
||||
puts "Test7== mix and reuse Boolean Queries: #{s.results.count}".yellow
|
||||
# The best thing about `boolean` queries is that we can very easily save these partial queries as Ruby blocks,
|
||||
# to mix and reuse them later, since we can call the `boolean` method multiple times.
|
||||
#
|
||||
|
||||
# Let's define the query for the _tags_ property,
|
||||
#
|
||||
tags_query = lambda do |boolean|
|
||||
boolean.should { string 'tags:ruby' }
|
||||
boolean.should { string 'tags:java' }
|
||||
end
|
||||
|
||||
# ... and a query for the _published_on_ property.
|
||||
published_on_query = lambda do |boolean|
|
||||
boolean.must { string 'published_on:[2011-01-01 TO 2011-01-02]' }
|
||||
end
|
||||
|
||||
# Now, we can use the `tags_query` on its own.
|
||||
#
|
||||
Tire.search('articles') { query { boolean &tags_query } }
|
||||
|
||||
# Or, we can combine it with the `published_on` query.
|
||||
#
|
||||
Tire.search('articles') do
|
||||
query do
|
||||
boolean &tags_query
|
||||
boolean &published_on_query
|
||||
end
|
||||
end
|
||||
|
||||
# _ElasticSearch_ supports many types of [queries](http://www.elasticsearch.org/guide/reference/query-dsl/).
|
||||
#
|
||||
# Eventually, _Tire_ will support all of them. So far, only these are supported:
|
||||
#
|
||||
# * [string](http://www.elasticsearch.org/guide/reference/query-dsl/query-string-query.html)
|
||||
# * [text](http://www.elasticsearch.org/guide/reference/query-dsl/text-query.html)
|
||||
# * [term](http://elasticsearch.org/guide/reference/query-dsl/term-query.html)
|
||||
# * [terms](http://elasticsearch.org/guide/reference/query-dsl/terms-query.html)
|
||||
# * [bool](http://www.elasticsearch.org/guide/reference/query-dsl/bool-query.html)
|
||||
# * [custom_score](http://www.elasticsearch.org/guide/reference/query-dsl/custom-score-query.html)
|
||||
# * [fuzzy](http://www.elasticsearch.org/guide/reference/query-dsl/fuzzy-query.html)
|
||||
# * [all](http://www.elasticsearch.org/guide/reference/query-dsl/match-all-query.html)
|
||||
# * [ids](http://www.elasticsearch.org/guide/reference/query-dsl/ids-query.html)
|
||||
|
||||
puts "Topic#### Faceted Search ==> SKIP".yellow
|
||||
|
||||
|
||||
|
||||
# # _ElasticSearch_ makes it trivial to retrieve complex aggregated data from our index/database,
|
||||
# # so called [_facets_](http://www.elasticsearch.org/guide/reference/api/search/facets/index.html).
|
||||
|
||||
# # Let's say we want to display article counts for every tag in the database.
|
||||
# # For that, we'll use a _terms_ facet.
|
||||
|
||||
# #
|
||||
# s = Tire.search 'articles' do
|
||||
|
||||
# # We will search for articles whose title begins with letter “T”,
|
||||
# #
|
||||
# query { string 'title:T*' }
|
||||
|
||||
# # and retrieve the counts “bucketed” by `tags`.
|
||||
# #
|
||||
# facet 'tags' do
|
||||
# terms :tags
|
||||
# end
|
||||
# end
|
||||
|
||||
# # As we see, our query has found two articles, and if you recall our articles from above,
|
||||
# # _Two_ is tagged with “ruby” and “python”, while _Three_ is tagged with “java”.
|
||||
# #
|
||||
# # Found 2 articles: Three, Two
|
||||
# #
|
||||
# # The counts shouldn't surprise us:
|
||||
# #
|
||||
# # Counts by tag:
|
||||
# # -------------------------
|
||||
# # ruby 1
|
||||
# # python 1
|
||||
# # java 1
|
||||
# #
|
||||
# puts "Found #{s.results.count} articles: #{s.results.map(&:title).join(', ')}"
|
||||
# puts "Counts by tag:", "-"*25
|
||||
# s.results.facets['tags']['terms'].each do |f|
|
||||
# puts "#{f['term'].ljust(10)} #{f['count']}"
|
||||
# end
|
||||
|
||||
# # These counts are based on the scope of our current query.
|
||||
# # What if we wanted to display aggregated counts by `tags` across the whole database?
|
||||
|
||||
# #
|
||||
# s = Tire.search 'articles' do
|
||||
|
||||
# # Let's repeat the search for “T”...
|
||||
# #
|
||||
# query { string 'title:T*' }
|
||||
|
||||
# facet 'global-tags', :global => true do
|
||||
|
||||
# # ...but set the `global` scope for the facet in this case.
|
||||
# #
|
||||
# terms :tags
|
||||
# end
|
||||
|
||||
# # We can even _combine_ facets scoped to the current query
|
||||
# # with globally scoped facets — we'll just use a different name.
|
||||
# #
|
||||
# facet 'current-tags' do
|
||||
# terms :tags
|
||||
# end
|
||||
# end
|
||||
|
||||
# # Aggregated results for the current query are the same as previously:
|
||||
# #
|
||||
# # Current query facets:
|
||||
# # -------------------------
|
||||
# # ruby 1
|
||||
# # python 1
|
||||
# # java 1
|
||||
# #
|
||||
# puts "Current query facets:", "-"*25
|
||||
# s.results.facets['current-tags']['terms'].each do |f|
|
||||
# puts "#{f['term'].ljust(10)} #{f['count']}"
|
||||
# end
|
||||
|
||||
# # On the other hand, aggregated results for the global scope include also
|
||||
# # tags for articles not matched by the query, such as “java” or “php”:
|
||||
# #
|
||||
# # Global facets:
|
||||
# # -------------------------
|
||||
# # ruby 3
|
||||
# # python 1
|
||||
# # php 1
|
||||
# # java 1
|
||||
# #
|
||||
# puts "Global facets:", "-"*25
|
||||
# s.results.facets['global-tags']['terms'].each do |f|
|
||||
# puts "#{f['term'].ljust(10)} #{f['count']}"
|
||||
# end
|
||||
|
||||
# # _ElasticSearch_ supports many advanced types of facets, such as those for computing statistics or geographical distance.
|
||||
# #
|
||||
# # Eventually, _Tire_ will support all of them. So far, only these are supported:
|
||||
# #
|
||||
# # * [terms](http://www.elasticsearch.org/guide/reference/api/search/facets/terms-facet.html)
|
||||
# # * [date](http://www.elasticsearch.org/guide/reference/api/search/facets/date-histogram-facet.html)
|
||||
# # * [range](http://www.elasticsearch.org/guide/reference/api/search/facets/range-facet.html)
|
||||
# # * [histogram](http://www.elasticsearch.org/guide/reference/api/search/facets/histogram-facet.html)
|
||||
# # * [statistical](http://www.elasticsearch.org/guide/reference/api/search/facets/statistical-facet.html)
|
||||
# # * [terms_stats](http://www.elasticsearch.org/guide/reference/api/search/facets/terms-stats-facet.html)
|
||||
# # * [query](http://www.elasticsearch.org/guide/reference/api/search/facets/query-facet.html)
|
||||
|
||||
# # We have seen that _ElasticSearch_ facets enable us to fetch complex aggregations from our data.
|
||||
# #
|
||||
# # They are frequently used for another feature, „faceted navigation“.
|
||||
# # We can be combine query and facets with
|
||||
# # [filters](http://elasticsearch.org/guide/reference/api/search/filter.html),
|
||||
# # so the returned documents are restricted by certain criteria — for example to a specific category —,
|
||||
# # but the aggregation calculations are still based on the original query.
|
||||
|
||||
|
||||
# #### Filtered Search
|
||||
|
||||
# # So, let's make our search a bit more complex. Let's search for articles whose titles begin
|
||||
# # with letter “T”, again, but filter the results, so only the articles tagged “ruby”
|
||||
# # are returned.
|
||||
# #
|
||||
# s = Tire.search 'articles' do
|
||||
|
||||
# # We will use just the same **query** as before.
|
||||
# #
|
||||
# query { string 'title:T*' }
|
||||
|
||||
# # But we will add a _terms_ **filter** based on tags.
|
||||
# #
|
||||
# filter :terms, :tags => ['ruby']
|
||||
|
||||
# # And, of course, our facet definition.
|
||||
# #
|
||||
# facet('tags') { terms :tags }
|
||||
|
||||
# end
|
||||
|
||||
# # We see that only the article _Two_ (tagged “ruby” and “python”) is returned,
|
||||
# # _not_ the article _Three_ (tagged “java”):
|
||||
# #
|
||||
# # * Two [tags: ruby, python]
|
||||
# #
|
||||
# s.results.each do |document|
|
||||
# puts "* #{ document.title } [tags: ]"
|
||||
# end
|
||||
|
||||
# # The _count_ for article _Three_'s tags, “java”, on the other hand, _is_ in fact included:
|
||||
# #
|
||||
# # Counts by tag:
|
||||
# # -------------------------
|
||||
# # ruby 1
|
||||
# # python 1
|
||||
# # java 1
|
||||
# #
|
||||
# puts "Counts by tag:", "-"*25
|
||||
# s.results.facets['tags']['terms'].each do |f|
|
||||
# puts "#{f['term'].ljust(10)} #{f['count']}"
|
||||
# end
|
||||
|
||||
# #### Sorting
|
||||
|
||||
# # By default, the results are sorted according to their relevancy.
|
||||
# #
|
||||
# s = Tire.search('articles') { query { string 'tags:ruby' } }
|
||||
|
||||
# s.results.each do |document|
|
||||
# puts "* #{ document.title } " +
|
||||
# "[tags: ; " +
|
||||
|
||||
# # The score is available as the `_score` property.
|
||||
# #
|
||||
# "score: #{document._score}]"
|
||||
# end
|
||||
|
||||
# # The results:
|
||||
# #
|
||||
# # * One [tags: ruby; score: 0.30685282]
|
||||
# # * Four [tags: ruby, php; score: 0.19178301]
|
||||
# # * Two [tags: ruby, python; score: 0.19178301]
|
||||
|
||||
# # But, what if we want to sort the results based on some other criteria,
|
||||
# # such as published date or product price? We can do that.
|
||||
# #
|
||||
# s = Tire.search 'articles' do
|
||||
|
||||
# # We will search for articles tagged “ruby”, again, ...
|
||||
# #
|
||||
# query { string 'tags:ruby' }
|
||||
|
||||
# # ... but will sort them by their `title`, in descending order.
|
||||
# #
|
||||
# sort { by :title, 'desc' }
|
||||
# end
|
||||
|
||||
# # The results:
|
||||
# #
|
||||
# # * Two
|
||||
# # * One
|
||||
# # * Four
|
||||
# #
|
||||
# s.results.each do |document|
|
||||
# puts "* #{ document.title }"
|
||||
# end
|
||||
|
||||
# # Of course, it's possible to combine more fields in the sorting definition.
|
||||
|
||||
# s = Tire.search 'articles' do
|
||||
|
||||
# # We will just get all articles in this case.
|
||||
# #
|
||||
# query { all }
|
||||
|
||||
# sort do
|
||||
|
||||
# # We will sort the results by their `published_on` property in _ascending_ order (the default),
|
||||
# #
|
||||
# by :published_on
|
||||
|
||||
# # and by their `title` property, in _descending_ order.
|
||||
# #
|
||||
# by :title, 'desc'
|
||||
# end
|
||||
# end
|
||||
|
||||
# # The results:
|
||||
# # * One (Published on: 2011-01-01)
|
||||
# # * Two (Published on: 2011-01-02)
|
||||
# # * Three (Published on: 2011-01-02)
|
||||
# # * Four (Published on: 2011-01-03)
|
||||
# #
|
||||
# s.results.each do |document|
|
||||
# puts "* #{ document.title.ljust(10) } (Published on: #{ document.published_on })"
|
||||
# end
|
||||
|
||||
# #### Highlighting
|
||||
|
||||
# # Often, we want to highlight the snippets matching our query in the displayed results.
|
||||
# # _ElasticSearch_ provides rich
|
||||
# # [highlighting](http://www.elasticsearch.org/guide/reference/api/search/highlighting.html)
|
||||
# # features, and _Tire_ makes them trivial to use.
|
||||
# #
|
||||
# s = Tire.search 'articles' do
|
||||
|
||||
# # Let's search for documents containing word “Two” in their titles,
|
||||
# query { string 'title:Two' }
|
||||
|
||||
# # and instruct _ElasticSearch_ to highlight relevant snippets.
|
||||
# #
|
||||
# highlight :title
|
||||
# end
|
||||
|
||||
# # The results:
|
||||
# # Title: Two; Highlighted: <em>Two</em>
|
||||
# #
|
||||
# s.results.each do |document|
|
||||
# puts "Title: #{ document.title }; Highlighted: #{document.highlight.title}"
|
||||
# end
|
||||
|
||||
# # We can configure many options for highlighting, such as:
|
||||
# #
|
||||
# s = Tire.search 'articles' do
|
||||
# query { string 'title:Two' }
|
||||
|
||||
# # • specify the fields to highlight
|
||||
# #
|
||||
# highlight :title, :body
|
||||
|
||||
# # • specify their individual options
|
||||
# #
|
||||
# highlight :title, :body => { :number_of_fragments => 0 }
|
||||
|
||||
# # • or specify global highlighting options, such as the wrapper tag
|
||||
# #
|
||||
# highlight :title, :body, :options => { :tag => '<strong class="highlight">' }
|
||||
# end
|
||||
|
||||
# #### Percolation
|
||||
|
||||
# # _ElasticSearch_ comes with one very interesting, and rather unique feature:
|
||||
# # [_percolation_](http://www.elasticsearch.org/guide/reference/api/percolate.html).
|
||||
|
||||
# # It works in a „reverse search“ manner to regular search workflow of adding
|
||||
# # documents to the index and then querying them.
|
||||
# # Percolation allows us to register a query, and ask if a specific document
|
||||
# # matches it, either on demand, or immediately as the document is being indexed.
|
||||
|
||||
# # Let's review an example for an index named _weather_.
|
||||
# # We will register three queries for percolation against this index.
|
||||
# #
|
||||
# index = Tire.index('weather') do
|
||||
# delete
|
||||
# create
|
||||
|
||||
# # First, a query named _warning_,
|
||||
# #
|
||||
# register_percolator_query('warning', :tags => ['warning']) { string 'warning OR severe OR extreme' }
|
||||
|
||||
# # a query named _tsunami_,
|
||||
# #
|
||||
# register_percolator_query('tsunami', :tags => ['tsunami']) { string 'tsunami' }
|
||||
|
||||
# # and a query named _floods_.
|
||||
# #
|
||||
# register_percolator_query('floods', :tags => ['floods']) { string 'flood*' }
|
||||
|
||||
# end
|
||||
|
||||
# # Notice, that we have added a _tags_ field to the query document, because it behaves
|
||||
# # just like any other document in _ElasticSearch_.
|
||||
|
||||
# # We will refresh the `_percolator` index for immediate access.
|
||||
# #
|
||||
# Tire.index('_percolator').refresh
|
||||
|
||||
# # Now, let's _percolate_ a document containing some trigger words against all registered queries.
|
||||
# #
|
||||
# matches = index.percolate(:message => '[Warning] Extreme flooding expected after tsunami wave.')
|
||||
|
||||
# # The result will contain, unsurprisingly, names of all the three registered queries:
|
||||
# #
|
||||
# # Matching queries: ["floods", "tsunami", "warning"]
|
||||
# #
|
||||
# puts "Matching queries: " + matches.inspect
|
||||
|
||||
# # We can filter the executed queries with a regular _ElasticSearch_ query passed as a block to
|
||||
# # the `percolate` method.
|
||||
# #
|
||||
# matches = index.percolate(:message => '[Warning] Extreme flooding expected after tsunami wave.') do
|
||||
# # Let's use a _terms_ query against the `tags` field.
|
||||
# term :tags, 'tsunami'
|
||||
# end
|
||||
|
||||
# # In this case, the result will contain only the name of the “tsunami” query.
|
||||
# #
|
||||
# # Matching queries: ["tsunami"]
|
||||
# #
|
||||
# puts "Matching queries: " + matches.inspect
|
||||
|
||||
# # What if we percolate another document, without the “tsunami” trigger word?
|
||||
# #
|
||||
# matches = index.percolate(:message => '[Warning] Extreme temperatures expected.') { term :tags, 'tsunami' }
|
||||
|
||||
# # As expected, we will get an empty array:
|
||||
# #
|
||||
# # Matching queries: []
|
||||
# #
|
||||
# puts "Matching queries: " + matches.inspect
|
||||
|
||||
# # Well, that's of course immensely useful for real-time search systems. But, there's more.
|
||||
# # We can _percolate_ a document _at the same time_ it is being stored in the index,
|
||||
# # getting back a list of matching queries.
|
||||
|
||||
# # Let's store a document with some trigger words in the index, and mark it for percolation.
|
||||
# #
|
||||
# response = index.store :message => '[Warning] Severe floods expected after tsunami wave.', :percolate => true
|
||||
|
||||
# # We will get the names of all matching queries in response.
|
||||
# #
|
||||
# # Matching queries: ["floods", "tsunami", "warning"]
|
||||
# #
|
||||
# puts "Matching queries: " + response['matches'].inspect
|
||||
|
||||
# # As with the _percolate_ example, we can filter the executed queries.
|
||||
# #
|
||||
# response = index.store :message => '[Warning] Severe floods expected after tsunami wave.',
|
||||
# # Let's use a simple string query for the “tsunami” tag.
|
||||
# :percolate => 'tags:tsunami'
|
||||
|
||||
# # Unsurprisingly, the response will contain just the name of the “tsunami” query.
|
||||
# #
|
||||
# # Matching queries: ["tsunami"]
|
||||
# #
|
||||
# puts "Matching queries: " + response['matches'].inspect
|
||||
|
||||
# ### ActiveModel Integration
|
||||
|
||||
# # As you can see, [_Tire_](https://github.com/karmi/tire) supports the
|
||||
# # main features of _ElasticSearch_ in Ruby.
|
||||
# #
|
||||
# # It allows you to create and delete indices, add documents, search them, retrieve the facets, highlight the results,
|
||||
# # and comes with a usable logging facility.
|
||||
# #
|
||||
# # Of course, the holy grail of any search library is easy, painless integration with your Ruby classes, and,
|
||||
# # most importantly, with ActiveRecord/ActiveModel classes.
|
||||
# #
|
||||
# # Please, check out the [README](https://github.com/karmi/tire/tree/master#readme) file for instructions
|
||||
# # how to include _Tire_-based search in your models..
|
||||
# #
|
||||
# # Send any feedback via Github issues, or ask questions in the [#elasticsearch](irc://irc.freenode.net/#elasticsearch) IRC channel.
|
|
@ -10,12 +10,22 @@ class Panel::News::FrontEnd::NewsBulletinsController < OrbitWidgetController
|
|||
|
||||
def index
|
||||
if !params[:search_query].blank?
|
||||
@news_bulletins = NewsBulletin.solr_search do
|
||||
fulltext params[:search_query] do
|
||||
fields(:text,:title=>2.0)
|
||||
end
|
||||
end.each_hit_with_result
|
||||
search_query =params[:search_query].gsub(/"/,"").split(" ")
|
||||
|
||||
words_query = lambda do |boolean|
|
||||
search_query.each do |word|
|
||||
boolean.should { string "title:#{word}" }
|
||||
#boolean.should { string "sub_title:#{word}" }
|
||||
#boolean.should { string "text:#{word}" }
|
||||
end
|
||||
end
|
||||
|
||||
search_result=Tire.search('news_bulletins') do
|
||||
query {boolean &words_query }
|
||||
#raise to_curl
|
||||
end.results.collect{|t| t.id}
|
||||
|
||||
@news_bulletins = NewsBulletin.can_display.any_in(_id:search_result).page( params[:page_main]).per(10)
|
||||
else
|
||||
date_now = Time.now
|
||||
if !params[:category_id].blank?
|
||||
|
|
|
@ -5,16 +5,13 @@ class NewsBulletin
|
|||
include Mongoid::Timestamps
|
||||
include Mongoid::MultiParameterAttributes
|
||||
include Impressionist::Impressionable
|
||||
# include OrbitBasis::BaseModel
|
||||
# include OrbitSearchLib::ObjectSearchable
|
||||
# include NccuSearch
|
||||
include Tire::Model::Search
|
||||
include Tire::Model::Callbacks
|
||||
# include Redis::Objects
|
||||
include Mongoid::BaseModel
|
||||
|
||||
include Sunspot::Mongoid
|
||||
|
||||
|
||||
# scope :searchable,where(:is_checked=>true,:is_hidden=>false,:is_pending=>false)
|
||||
|
||||
scope :searchable,where(:is_checked=>true,:is_hidden=>false,:is_pending=>false)
|
||||
|
||||
is_impressionable :counter_cache => { :column_name => :view_count }
|
||||
|
||||
|
@ -64,61 +61,43 @@ class NewsBulletin
|
|||
|
||||
after_save :save_news_bulletin_links
|
||||
after_save :save_news_bulletin_files
|
||||
# include OrbitBasis::ClassMethods
|
||||
|
||||
|
||||
searchable do
|
||||
text :title do
|
||||
titles = ""
|
||||
titles << (self.title.zh_tw.nil? ? '':self.title.zh_tw)
|
||||
titles << (self.title.en.nil? ? '':self.title.en)
|
||||
#(titles << self.title.en )unless self.title.nil?
|
||||
doc = Nokogiri::HTML(titles)
|
||||
doc.text
|
||||
#VALID_LOCALES
|
||||
end
|
||||
|
||||
text :text do
|
||||
texts = ""
|
||||
texts << (self.text.zh_tw.nil? ? '':self.text.zh_tw)
|
||||
texts << (self.text.en.nil? ? '':self.text.en)
|
||||
#texts << self.text.en )unless self.text.en.nil?
|
||||
doc = Nokogiri::HTML(texts)
|
||||
doc.text
|
||||
#VALID_LOCALES
|
||||
end
|
||||
# text :sub_titles do
|
||||
# self.subtitle.zh_tw
|
||||
# #VALID_LOCALES
|
||||
# end
|
||||
# text :text do
|
||||
# self.text.zh_tw
|
||||
# #VALID_LOCALES
|
||||
# end
|
||||
# text :content, :publish_month
|
||||
# text :comments do
|
||||
# comments.map(&:content)
|
||||
# end
|
||||
# time :published_at
|
||||
# string :publish_month
|
||||
end
|
||||
# Tire.index 'news_bulletin' do
|
||||
# delete
|
||||
# create :mappings =>{
|
||||
# :news_bulletin_by_title => {
|
||||
# :properties=> {
|
||||
# :title => { :type => 'string', :index => 'not_analyzed', :include_in_all => false },
|
||||
# :body => {}
|
||||
# }
|
||||
# }
|
||||
# :news_bulletin_by_body => {
|
||||
# :properties=> {
|
||||
# :body => { :type => 'string', :index => 'not_analyzed', :include_in_all => false },
|
||||
# }
|
||||
# }
|
||||
# }
|
||||
# end
|
||||
# mapping do
|
||||
# indexes :title, :analyzer => 'cjk', :boost => 10
|
||||
# indexes :sub_titles, :analyzer => 'cjk', :boost => 5
|
||||
# indexes :text, :analyzer => 'cjk'
|
||||
# end
|
||||
|
||||
# def to_indexed_json
|
||||
# titles = title.zh_tw + title.en
|
||||
# sub_titles = subtitle.zh_tw + subtitle.en
|
||||
# texts = text.zh_tw + text.en
|
||||
# {
|
||||
# :id => id,
|
||||
# :title => titles,
|
||||
# :sub_titles => sub_titles,
|
||||
# :text => texts
|
||||
# }.to_json
|
||||
# end
|
||||
def type
|
||||
"news_bulletin"
|
||||
end
|
||||
|
||||
def to_indexed_json
|
||||
titles = title.zh_tw #+ title.en
|
||||
sub_titles = subtitle.zh_tw #+ subtitle.en
|
||||
texts = text.zh_tw #+ text.en
|
||||
{
|
||||
:_id => _id,
|
||||
:title => Nokogiri::HTML(titles).text,
|
||||
:sub_title => Nokogiri::HTML(sub_titles).text,
|
||||
:text => Nokogiri::HTML(texts).text
|
||||
}.to_json
|
||||
end
|
||||
|
||||
def self.search( search = nil, category_id = nil )
|
||||
if category_id.to_s.size > 0 and search.to_s.size > 0
|
||||
|
|
Loading…
Reference in New Issue