solrsam 0.4.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +5 -0
- data/Gemfile +5 -0
- data/Gemfile.lock +22 -0
- data/LICENSE +23 -0
- data/README.rdoc +115 -0
- data/Rakefile +18 -0
- data/config/solr/conf/elevate.xml +31 -0
- data/config/solr/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/config/solr/conf/protwords.txt +22 -0
- data/config/solr/conf/schema.xml +237 -0
- data/config/solr/conf/solrconfig.xml +430 -0
- data/config/solr/conf/spellings.txt +2 -0
- data/config/solr/conf/stopwords.txt +56 -0
- data/config/solr/conf/synonyms.txt +24 -0
- data/config/solr/conf/xslt/example.xsl +132 -0
- data/config/solr/conf/xslt/example_atom.xsl +67 -0
- data/config/solr/conf/xslt/example_rss.xsl +66 -0
- data/config/solr/conf/xslt/luke.xsl +337 -0
- data/config/solr.yml +12 -0
- data/config/solr.yml.example +13 -0
- data/lib/rails/generators/solrsan/config/config_generator.rb +23 -0
- data/lib/rails/generators/solrsan/config/templates/solr.yml +13 -0
- data/lib/rails/generators/solrsan/config/templates/solrsan.rb +5 -0
- data/lib/rails/generators/solrsan_generator.rb +11 -0
- data/lib/solrsam/capistrano.rb +31 -0
- data/lib/solrsam/config.rb +25 -0
- data/lib/solrsam/indexer.rb +83 -0
- data/lib/solrsam/search.rb +195 -0
- data/lib/solrsam/version.rb +3 -0
- data/lib/solrsam.rb +12 -0
- data/lib/tasks/solr.rake +71 -0
- data/solrsam.gemspec +25 -0
- data/test/models/document.rb +11 -0
- data/test/search_test_helper.rb +13 -0
- data/test/test_helper.rb +27 -0
- data/test/unit/indexer_test.rb +25 -0
- data/test/unit/search_test.rb +251 -0
- metadata +124 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
GEM
|
2
|
+
remote: http://rubygems.org/
|
3
|
+
specs:
|
4
|
+
activemodel (3.2.0)
|
5
|
+
activesupport (= 3.2.0)
|
6
|
+
builder (~> 3.0.0)
|
7
|
+
activesupport (3.2.0)
|
8
|
+
i18n (~> 0.6)
|
9
|
+
multi_json (~> 1.0)
|
10
|
+
builder (3.0.0)
|
11
|
+
i18n (0.6.0)
|
12
|
+
multi_json (1.0.4)
|
13
|
+
rsolr (1.0.0)
|
14
|
+
builder (>= 2.1.2)
|
15
|
+
|
16
|
+
PLATFORMS
|
17
|
+
ruby
|
18
|
+
|
19
|
+
DEPENDENCIES
|
20
|
+
activemodel
|
21
|
+
activesupport
|
22
|
+
rsolr (= 1.0.0)
|
data/LICENSE
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
MIT License
|
2
|
+
---
|
3
|
+
|
4
|
+
Copyright (c) 2010 Tommy Chheng
|
5
|
+
|
6
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
7
|
+
of this software and associated documentation files (the "Software"), to deal
|
8
|
+
in the Software without restriction, including without limitation the rights
|
9
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
10
|
+
copies of the Software, and to permit persons to whom the Software is
|
11
|
+
furnished to do so, subject to the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be included in
|
14
|
+
all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
17
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
18
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
19
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
20
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
21
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
22
|
+
THE SOFTWARE.
|
23
|
+
|
data/README.rdoc
ADDED
@@ -0,0 +1,115 @@
|
|
1
|
+
= solrsan
|
2
|
+
|
3
|
+
http://github.com/tc/solrsan
|
4
|
+
|
5
|
+
This gem is a lightweight wrapper for the Apache Solr API.
|
6
|
+
|
7
|
+
Before you start, read the documentation for solr at http://wiki.apache.org/solr
|
8
|
+
|
9
|
+
It'll be invaluable for knowing parameters and error messages.
|
10
|
+
I made a few test cases for further examples at http://github.com/tc/solrsan/tree/master/test/unit
|
11
|
+
|
12
|
+
=== HOWTO
|
13
|
+
Install Jetty
|
14
|
+
|
15
|
+
wget http://download.eclipse.org/jetty/7.3.0.v20110203/dist/jetty-distribution-7.3.0.v20110203.tar.gz
|
16
|
+
tar -zxvf jetty-distribution-*.tar.gz
|
17
|
+
rm jetty-distribution-*.tar.gz
|
18
|
+
mv jetty-distribution-* /usr/local
|
19
|
+
ln -s jetty-distribution-* jetty
|
20
|
+
|
21
|
+
Install solr
|
22
|
+
|
23
|
+
|
24
|
+
wget http://www.ecoficial.com/apachemirror/lucene/solr/3.1.0/apache-solr-3.1.0.tgz
|
25
|
+
tar -zxvf apache-solr-*.tgz
|
26
|
+
cd apache-solr-*
|
27
|
+
cp dist/apache-solr-*.war /usr/local/jetty/webapps/solr.war
|
28
|
+
|
29
|
+
Add solrsan to your Ruby application's Gemfile:
|
30
|
+
gem "solrsan"
|
31
|
+
|
32
|
+
Create solr configuration files using:
|
33
|
+
rails generate solrsan:config
|
34
|
+
|
35
|
+
The generator will copy the following files into your application.
|
36
|
+
|
37
|
+
config/solr.yml
|
38
|
+
config/solr
|
39
|
+
config/initializers/solrsan.rb
|
40
|
+
lib/tasks/solr.rake
|
41
|
+
|
42
|
+
Edit the config/solr.yml for your directory paths.
|
43
|
+
|
44
|
+
The rake file will add these rake tasks:
|
45
|
+
|
46
|
+
rake solr:start
|
47
|
+
rake solr:stop
|
48
|
+
rake solr:clear_index
|
49
|
+
rake solr:index
|
50
|
+
|
51
|
+
you will need to alter clear_index/index to match your models
|
52
|
+
|
53
|
+
Deploy tasks via capistrano:
|
54
|
+
add to your deploy.rb
|
55
|
+
|
56
|
+
require 'solrsan/capistrano'
|
57
|
+
|
58
|
+
This will add the following methods which will just call the
|
59
|
+
corresponding rake tasks:
|
60
|
+
|
61
|
+
cap solr:start
|
62
|
+
cap solr:stop
|
63
|
+
cap solr:reindex
|
64
|
+
|
65
|
+
=== Indexing documents:
|
66
|
+
Edit config/solr/conf/schema.xml to state the types of fields you want
|
67
|
+
to index. You can use dynamic fields as well.
|
68
|
+
|
69
|
+
These fields are required for each solr document and are automatically
|
70
|
+
generated:
|
71
|
+
|
72
|
+
id, db_id, type
|
73
|
+
|
74
|
+
In your model, define as_solr_document and return a hash with specific fields.
|
75
|
+
|
76
|
+
|
77
|
+
class Document < ActiveRecord::Base
|
78
|
+
include Solrsan::Search
|
79
|
+
after_save :index
|
80
|
+
before_destroy :destroy_index_document
|
81
|
+
|
82
|
+
def as_solr_document
|
83
|
+
{:content => "hi"}
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
|
88
|
+
In each model, you can include a Solrsan::Search module which will include a few interface helper methods:
|
89
|
+
index
|
90
|
+
destroy_index_document
|
91
|
+
search(params)
|
92
|
+
|
93
|
+
=== Search:
|
94
|
+
A simple search query:
|
95
|
+
Document.search(:q => "hello world")
|
96
|
+
|
97
|
+
More searching examples can be seen in test/unit/search_test.rb
|
98
|
+
|
99
|
+
== Changelog
|
100
|
+
0.0.33
|
101
|
+
Reverted Hashwithindifferentaccess for request parsing, buggy with will_paginate.
|
102
|
+
|
103
|
+
0.0.32
|
104
|
+
Using Hashwithindifferentaccess for request parsing.
|
105
|
+
|
106
|
+
0.0.31
|
107
|
+
Usable version!
|
108
|
+
|
109
|
+
0.0.1
|
110
|
+
First release.
|
111
|
+
|
112
|
+
== Copyright
|
113
|
+
|
114
|
+
Copyright (c) 2011 Tommy Chheng. See LICENSE for details.
|
115
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'bundler'
|
2
|
+
require 'rake/testtask'
|
3
|
+
Bundler::GemHelper.install_tasks
|
4
|
+
Dir[File.join(File.dirname(__FILE__), "lib", "tasks", "**", "*.rake")].each { |ext| load ext }
|
5
|
+
|
6
|
+
desc "Default: run all tests"
|
7
|
+
task :default => :test
|
8
|
+
|
9
|
+
desc "Run tests"
|
10
|
+
task :test => %w(test:units)
|
11
|
+
namespace :test do
|
12
|
+
desc "Run unit tests"
|
13
|
+
Rake::TestTask.new(:units) do |t|
|
14
|
+
t.libs << 'lib' << 'test'
|
15
|
+
t.test_files = FileList["test/unit/*_test.rb", "test/unit/*/*_test.rb"]
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
@@ -0,0 +1,31 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8" ?>
|
2
|
+
<!--
|
3
|
+
Licensed to the Apache Software Foundation (ASF) under one or more
|
4
|
+
contributor license agreements. See the NOTICE file distributed with
|
5
|
+
this work for additional information regarding copyright ownership.
|
6
|
+
The ASF licenses this file to You under the Apache License, Version 2.0
|
7
|
+
(the "License"); you may not use this file except in compliance with
|
8
|
+
the License. You may obtain a copy of the License at
|
9
|
+
|
10
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
11
|
+
|
12
|
+
Unless required by applicable law or agreed to in writing, software
|
13
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
14
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
15
|
+
See the License for the specific language governing permissions and
|
16
|
+
limitations under the License.
|
17
|
+
-->
|
18
|
+
|
19
|
+
<!-- If this file is found in the config directory, it will only be
|
20
|
+
loaded once at startup. If it is found in Solr's data
|
21
|
+
directory, it will be re-loaded every commit.
|
22
|
+
-->
|
23
|
+
|
24
|
+
<elevate>
|
25
|
+
<query text="foo bar">
|
26
|
+
<doc id="1" />
|
27
|
+
<doc id="2" />
|
28
|
+
<doc id="3" />
|
29
|
+
</query>
|
30
|
+
|
31
|
+
</elevate>
|
@@ -0,0 +1,246 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
# Syntax:
|
14
|
+
# "source" => "target"
|
15
|
+
# "source".length() > 0 (source cannot be empty.)
|
16
|
+
# "target".length() >= 0 (target can be empty.)
|
17
|
+
|
18
|
+
# example:
|
19
|
+
# "À" => "A"
|
20
|
+
# "\u00C0" => "A"
|
21
|
+
# "\u00C0" => "\u0041"
|
22
|
+
# "ß" => "ss"
|
23
|
+
# "\t" => " "
|
24
|
+
# "\n" => ""
|
25
|
+
|
26
|
+
# À => A
|
27
|
+
"\u00C0" => "A"
|
28
|
+
|
29
|
+
# Á => A
|
30
|
+
"\u00C1" => "A"
|
31
|
+
|
32
|
+
# Â => A
|
33
|
+
"\u00C2" => "A"
|
34
|
+
|
35
|
+
# Ã => A
|
36
|
+
"\u00C3" => "A"
|
37
|
+
|
38
|
+
# Ä => A
|
39
|
+
"\u00C4" => "A"
|
40
|
+
|
41
|
+
# Å => A
|
42
|
+
"\u00C5" => "A"
|
43
|
+
|
44
|
+
# Æ => AE
|
45
|
+
"\u00C6" => "AE"
|
46
|
+
|
47
|
+
# Ç => C
|
48
|
+
"\u00C7" => "C"
|
49
|
+
|
50
|
+
# È => E
|
51
|
+
"\u00C8" => "E"
|
52
|
+
|
53
|
+
# É => E
|
54
|
+
"\u00C9" => "E"
|
55
|
+
|
56
|
+
# Ê => E
|
57
|
+
"\u00CA" => "E"
|
58
|
+
|
59
|
+
# Ë => E
|
60
|
+
"\u00CB" => "E"
|
61
|
+
|
62
|
+
# Ì => I
|
63
|
+
"\u00CC" => "I"
|
64
|
+
|
65
|
+
# Í => I
|
66
|
+
"\u00CD" => "I"
|
67
|
+
|
68
|
+
# Î => I
|
69
|
+
"\u00CE" => "I"
|
70
|
+
|
71
|
+
# Ï => I
|
72
|
+
"\u00CF" => "I"
|
73
|
+
|
74
|
+
# IJ => IJ
|
75
|
+
"\u0132" => "IJ"
|
76
|
+
|
77
|
+
# Ð => D
|
78
|
+
"\u00D0" => "D"
|
79
|
+
|
80
|
+
# Ñ => N
|
81
|
+
"\u00D1" => "N"
|
82
|
+
|
83
|
+
# Ò => O
|
84
|
+
"\u00D2" => "O"
|
85
|
+
|
86
|
+
# Ó => O
|
87
|
+
"\u00D3" => "O"
|
88
|
+
|
89
|
+
# Ô => O
|
90
|
+
"\u00D4" => "O"
|
91
|
+
|
92
|
+
# Õ => O
|
93
|
+
"\u00D5" => "O"
|
94
|
+
|
95
|
+
# Ö => O
|
96
|
+
"\u00D6" => "O"
|
97
|
+
|
98
|
+
# Ø => O
|
99
|
+
"\u00D8" => "O"
|
100
|
+
|
101
|
+
# Œ => OE
|
102
|
+
"\u0152" => "OE"
|
103
|
+
|
104
|
+
# Þ
|
105
|
+
"\u00DE" => "TH"
|
106
|
+
|
107
|
+
# Ù => U
|
108
|
+
"\u00D9" => "U"
|
109
|
+
|
110
|
+
# Ú => U
|
111
|
+
"\u00DA" => "U"
|
112
|
+
|
113
|
+
# Û => U
|
114
|
+
"\u00DB" => "U"
|
115
|
+
|
116
|
+
# Ü => U
|
117
|
+
"\u00DC" => "U"
|
118
|
+
|
119
|
+
# Ý => Y
|
120
|
+
"\u00DD" => "Y"
|
121
|
+
|
122
|
+
# Ÿ => Y
|
123
|
+
"\u0178" => "Y"
|
124
|
+
|
125
|
+
# à => a
|
126
|
+
"\u00E0" => "a"
|
127
|
+
|
128
|
+
# á => a
|
129
|
+
"\u00E1" => "a"
|
130
|
+
|
131
|
+
# â => a
|
132
|
+
"\u00E2" => "a"
|
133
|
+
|
134
|
+
# ã => a
|
135
|
+
"\u00E3" => "a"
|
136
|
+
|
137
|
+
# ä => a
|
138
|
+
"\u00E4" => "a"
|
139
|
+
|
140
|
+
# å => a
|
141
|
+
"\u00E5" => "a"
|
142
|
+
|
143
|
+
# æ => ae
|
144
|
+
"\u00E6" => "ae"
|
145
|
+
|
146
|
+
# ç => c
|
147
|
+
"\u00E7" => "c"
|
148
|
+
|
149
|
+
# è => e
|
150
|
+
"\u00E8" => "e"
|
151
|
+
|
152
|
+
# é => e
|
153
|
+
"\u00E9" => "e"
|
154
|
+
|
155
|
+
# ê => e
|
156
|
+
"\u00EA" => "e"
|
157
|
+
|
158
|
+
# ë => e
|
159
|
+
"\u00EB" => "e"
|
160
|
+
|
161
|
+
# ì => i
|
162
|
+
"\u00EC" => "i"
|
163
|
+
|
164
|
+
# í => i
|
165
|
+
"\u00ED" => "i"
|
166
|
+
|
167
|
+
# î => i
|
168
|
+
"\u00EE" => "i"
|
169
|
+
|
170
|
+
# ï => i
|
171
|
+
"\u00EF" => "i"
|
172
|
+
|
173
|
+
# ij => ij
|
174
|
+
"\u0133" => "ij"
|
175
|
+
|
176
|
+
# ð => d
|
177
|
+
"\u00F0" => "d"
|
178
|
+
|
179
|
+
# ñ => n
|
180
|
+
"\u00F1" => "n"
|
181
|
+
|
182
|
+
# ò => o
|
183
|
+
"\u00F2" => "o"
|
184
|
+
|
185
|
+
# ó => o
|
186
|
+
"\u00F3" => "o"
|
187
|
+
|
188
|
+
# ô => o
|
189
|
+
"\u00F4" => "o"
|
190
|
+
|
191
|
+
# õ => o
|
192
|
+
"\u00F5" => "o"
|
193
|
+
|
194
|
+
# ö => o
|
195
|
+
"\u00F6" => "o"
|
196
|
+
|
197
|
+
# ø => o
|
198
|
+
"\u00F8" => "o"
|
199
|
+
|
200
|
+
# œ => oe
|
201
|
+
"\u0153" => "oe"
|
202
|
+
|
203
|
+
# ß => ss
|
204
|
+
"\u00DF" => "ss"
|
205
|
+
|
206
|
+
# þ => th
|
207
|
+
"\u00FE" => "th"
|
208
|
+
|
209
|
+
# ù => u
|
210
|
+
"\u00F9" => "u"
|
211
|
+
|
212
|
+
# ú => u
|
213
|
+
"\u00FA" => "u"
|
214
|
+
|
215
|
+
# û => u
|
216
|
+
"\u00FB" => "u"
|
217
|
+
|
218
|
+
# ü => u
|
219
|
+
"\u00FC" => "u"
|
220
|
+
|
221
|
+
# ý => y
|
222
|
+
"\u00FD" => "y"
|
223
|
+
|
224
|
+
# ÿ => y
|
225
|
+
"\u00FF" => "y"
|
226
|
+
|
227
|
+
# ff => ff
|
228
|
+
"\uFB00" => "ff"
|
229
|
+
|
230
|
+
# fi => fi
|
231
|
+
"\uFB01" => "fi"
|
232
|
+
|
233
|
+
# fl => fl
|
234
|
+
"\uFB02" => "fl"
|
235
|
+
|
236
|
+
# ffi => ffi
|
237
|
+
"\uFB03" => "ffi"
|
238
|
+
|
239
|
+
# ffl => ffl
|
240
|
+
"\uFB04" => "ffl"
|
241
|
+
|
242
|
+
# ſt => ft
|
243
|
+
"\uFB05" => "ft"
|
244
|
+
|
245
|
+
# st => st
|
246
|
+
"\uFB06" => "st"
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
#-----------------------------------------------------------------------
|
14
|
+
# Use a protected word file to protect against the stemmer reducing two
|
15
|
+
# unrelated words to the same base word.
|
16
|
+
|
17
|
+
# Some non-words that normally won't be encountered,
|
18
|
+
# just to test that they won't be stemmed.
|
19
|
+
dontstems
|
20
|
+
zwhacky
|
21
|
+
|
22
|
+
|