thinking-sphinx 1.2.12

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.
Files changed (95) hide show
  1. data/LICENCE +20 -0
  2. data/README.textile +157 -0
  3. data/VERSION.yml +4 -0
  4. data/lib/thinking_sphinx.rb +211 -0
  5. data/lib/thinking_sphinx/active_record.rb +307 -0
  6. data/lib/thinking_sphinx/active_record/attribute_updates.rb +48 -0
  7. data/lib/thinking_sphinx/active_record/delta.rb +87 -0
  8. data/lib/thinking_sphinx/active_record/has_many_association.rb +28 -0
  9. data/lib/thinking_sphinx/active_record/scopes.rb +39 -0
  10. data/lib/thinking_sphinx/adapters/abstract_adapter.rb +42 -0
  11. data/lib/thinking_sphinx/adapters/mysql_adapter.rb +54 -0
  12. data/lib/thinking_sphinx/adapters/postgresql_adapter.rb +136 -0
  13. data/lib/thinking_sphinx/association.rb +164 -0
  14. data/lib/thinking_sphinx/attribute.rb +342 -0
  15. data/lib/thinking_sphinx/class_facet.rb +15 -0
  16. data/lib/thinking_sphinx/configuration.rb +282 -0
  17. data/lib/thinking_sphinx/core/array.rb +7 -0
  18. data/lib/thinking_sphinx/core/string.rb +15 -0
  19. data/lib/thinking_sphinx/deltas.rb +30 -0
  20. data/lib/thinking_sphinx/deltas/datetime_delta.rb +50 -0
  21. data/lib/thinking_sphinx/deltas/default_delta.rb +68 -0
  22. data/lib/thinking_sphinx/deltas/delayed_delta.rb +30 -0
  23. data/lib/thinking_sphinx/deltas/delayed_delta/delta_job.rb +24 -0
  24. data/lib/thinking_sphinx/deltas/delayed_delta/flag_as_deleted_job.rb +27 -0
  25. data/lib/thinking_sphinx/deltas/delayed_delta/job.rb +26 -0
  26. data/lib/thinking_sphinx/deploy/capistrano.rb +100 -0
  27. data/lib/thinking_sphinx/excerpter.rb +22 -0
  28. data/lib/thinking_sphinx/facet.rb +125 -0
  29. data/lib/thinking_sphinx/facet_search.rb +134 -0
  30. data/lib/thinking_sphinx/field.rb +82 -0
  31. data/lib/thinking_sphinx/index.rb +99 -0
  32. data/lib/thinking_sphinx/index/builder.rb +286 -0
  33. data/lib/thinking_sphinx/index/faux_column.rb +110 -0
  34. data/lib/thinking_sphinx/property.rb +162 -0
  35. data/lib/thinking_sphinx/rails_additions.rb +150 -0
  36. data/lib/thinking_sphinx/search.rb +707 -0
  37. data/lib/thinking_sphinx/search_methods.rb +421 -0
  38. data/lib/thinking_sphinx/source.rb +150 -0
  39. data/lib/thinking_sphinx/source/internal_properties.rb +46 -0
  40. data/lib/thinking_sphinx/source/sql.rb +128 -0
  41. data/lib/thinking_sphinx/tasks.rb +165 -0
  42. data/rails/init.rb +14 -0
  43. data/spec/lib/thinking_sphinx/active_record/delta_spec.rb +130 -0
  44. data/spec/lib/thinking_sphinx/active_record/has_many_association_spec.rb +49 -0
  45. data/spec/lib/thinking_sphinx/active_record/scopes_spec.rb +96 -0
  46. data/spec/lib/thinking_sphinx/active_record_spec.rb +364 -0
  47. data/spec/lib/thinking_sphinx/association_spec.rb +239 -0
  48. data/spec/lib/thinking_sphinx/attribute_spec.rb +500 -0
  49. data/spec/lib/thinking_sphinx/configuration_spec.rb +268 -0
  50. data/spec/lib/thinking_sphinx/core/array_spec.rb +9 -0
  51. data/spec/lib/thinking_sphinx/core/string_spec.rb +9 -0
  52. data/spec/lib/thinking_sphinx/excerpter_spec.rb +49 -0
  53. data/spec/lib/thinking_sphinx/facet_search_spec.rb +176 -0
  54. data/spec/lib/thinking_sphinx/facet_spec.rb +333 -0
  55. data/spec/lib/thinking_sphinx/field_spec.rb +154 -0
  56. data/spec/lib/thinking_sphinx/index/builder_spec.rb +455 -0
  57. data/spec/lib/thinking_sphinx/index/faux_column_spec.rb +30 -0
  58. data/spec/lib/thinking_sphinx/index_spec.rb +45 -0
  59. data/spec/lib/thinking_sphinx/rails_additions_spec.rb +203 -0
  60. data/spec/lib/thinking_sphinx/search_methods_spec.rb +152 -0
  61. data/spec/lib/thinking_sphinx/search_spec.rb +1092 -0
  62. data/spec/lib/thinking_sphinx/source_spec.rb +227 -0
  63. data/spec/lib/thinking_sphinx_spec.rb +162 -0
  64. data/tasks/distribution.rb +50 -0
  65. data/tasks/rails.rake +1 -0
  66. data/tasks/testing.rb +83 -0
  67. data/vendor/after_commit/LICENSE +20 -0
  68. data/vendor/after_commit/README +16 -0
  69. data/vendor/after_commit/Rakefile +22 -0
  70. data/vendor/after_commit/init.rb +8 -0
  71. data/vendor/after_commit/lib/after_commit.rb +45 -0
  72. data/vendor/after_commit/lib/after_commit/active_record.rb +114 -0
  73. data/vendor/after_commit/lib/after_commit/connection_adapters.rb +103 -0
  74. data/vendor/after_commit/test/after_commit_test.rb +53 -0
  75. data/vendor/delayed_job/lib/delayed/job.rb +251 -0
  76. data/vendor/delayed_job/lib/delayed/message_sending.rb +7 -0
  77. data/vendor/delayed_job/lib/delayed/performable_method.rb +55 -0
  78. data/vendor/delayed_job/lib/delayed/worker.rb +54 -0
  79. data/vendor/riddle/lib/riddle.rb +30 -0
  80. data/vendor/riddle/lib/riddle/client.rb +635 -0
  81. data/vendor/riddle/lib/riddle/client/filter.rb +53 -0
  82. data/vendor/riddle/lib/riddle/client/message.rb +66 -0
  83. data/vendor/riddle/lib/riddle/client/response.rb +84 -0
  84. data/vendor/riddle/lib/riddle/configuration.rb +33 -0
  85. data/vendor/riddle/lib/riddle/configuration/distributed_index.rb +48 -0
  86. data/vendor/riddle/lib/riddle/configuration/index.rb +142 -0
  87. data/vendor/riddle/lib/riddle/configuration/indexer.rb +19 -0
  88. data/vendor/riddle/lib/riddle/configuration/remote_index.rb +17 -0
  89. data/vendor/riddle/lib/riddle/configuration/searchd.rb +25 -0
  90. data/vendor/riddle/lib/riddle/configuration/section.rb +43 -0
  91. data/vendor/riddle/lib/riddle/configuration/source.rb +23 -0
  92. data/vendor/riddle/lib/riddle/configuration/sql_source.rb +34 -0
  93. data/vendor/riddle/lib/riddle/configuration/xml_source.rb +28 -0
  94. data/vendor/riddle/lib/riddle/controller.rb +53 -0
  95. metadata +172 -0
@@ -0,0 +1,7 @@
1
+ module SearchAsArray
2
+ def ===(object)
3
+ object.is_a?(ThinkingSphinx::Search) || super
4
+ end
5
+ end
6
+
7
+ Array.extend SearchAsArray
@@ -0,0 +1,15 @@
1
+ require 'zlib'
2
+
3
+ module ThinkingSphinx
4
+ module Core
5
+ module String
6
+ def to_crc32
7
+ Zlib.crc32 self
8
+ end
9
+ end
10
+ end
11
+ end
12
+
13
+ class String
14
+ include ThinkingSphinx::Core::String
15
+ end
@@ -0,0 +1,30 @@
1
+ require 'thinking_sphinx/deltas/default_delta'
2
+ require 'thinking_sphinx/deltas/delayed_delta'
3
+ require 'thinking_sphinx/deltas/datetime_delta'
4
+
5
+ module ThinkingSphinx
6
+ module Deltas
7
+ def self.parse(index)
8
+ delta_option = index.local_options.delete(:delta)
9
+ case delta_option
10
+ when TrueClass, :default
11
+ DefaultDelta.new index, index.local_options
12
+ when :delayed
13
+ DelayedDelta.new index, index.local_options
14
+ when :datetime
15
+ DatetimeDelta.new index, index.local_options
16
+ when FalseClass, nil
17
+ nil
18
+ else
19
+ if delta_option.is_a?(String)
20
+ delta_option = Kernel.const_get(delta_option)
21
+ end
22
+ if delta_option.ancestors.include?(ThinkingSphinx::Deltas::DefaultDelta)
23
+ delta_option.new index, index.local_options
24
+ else
25
+ raise "Unknown delta type"
26
+ end
27
+ end
28
+ end
29
+ end
30
+ end
@@ -0,0 +1,50 @@
1
+ module ThinkingSphinx
2
+ module Deltas
3
+ class DatetimeDelta < ThinkingSphinx::Deltas::DefaultDelta
4
+ attr_accessor :column, :threshold
5
+
6
+ def initialize(index, options)
7
+ @index = index
8
+ @column = options.delete(:delta_column) || :updated_at
9
+ @threshold = options.delete(:threshold) || 1.day
10
+ end
11
+
12
+ def index(model, instance = nil)
13
+ # do nothing
14
+ true
15
+ end
16
+
17
+ def delayed_index(model)
18
+ config = ThinkingSphinx::Configuration.instance
19
+ rotate = ThinkingSphinx.sphinx_running? ? "--rotate" : ""
20
+
21
+ output = `#{config.bin_path}#{config.indexer_binary_name} --config #{config.config_file} #{rotate} #{delta_index_name model}`
22
+ output += `#{config.bin_path}#{config.indexer_binary_name} --config #{config.config_file} #{rotate} --merge #{core_index_name model} #{delta_index_name model} --merge-dst-range sphinx_deleted 0 0`
23
+ puts output unless ThinkingSphinx.suppress_delta_output?
24
+
25
+ true
26
+ end
27
+
28
+ def toggle(instance)
29
+ # do nothing
30
+ end
31
+
32
+ def toggled(instance)
33
+ instance.send(@column) > @threshold.ago
34
+ end
35
+
36
+ def reset_query(model)
37
+ nil
38
+ end
39
+
40
+ def clause(model, toggled)
41
+ if toggled
42
+ "#{model.quoted_table_name}.#{model.connection.quote_column_name(@column.to_s)}" +
43
+ " > #{adapter.time_difference(@threshold)}"
44
+ else
45
+ nil
46
+ end
47
+ end
48
+ end
49
+ end
50
+ end
@@ -0,0 +1,68 @@
1
+ module ThinkingSphinx
2
+ module Deltas
3
+ class DefaultDelta
4
+ attr_accessor :column
5
+
6
+ def initialize(index, options)
7
+ @index = index
8
+ @column = options.delete(:delta_column) || :delta
9
+ end
10
+
11
+ def index(model, instance = nil)
12
+ return true unless ThinkingSphinx.updates_enabled? &&
13
+ ThinkingSphinx.deltas_enabled?
14
+ return true if instance && !toggled(instance)
15
+
16
+ config = ThinkingSphinx::Configuration.instance
17
+ client = Riddle::Client.new config.address, config.port
18
+ rotate = ThinkingSphinx.sphinx_running? ? "--rotate" : ""
19
+
20
+ output = `#{config.bin_path}#{config.indexer_binary_name} --config #{config.config_file} #{rotate} #{delta_index_name model}`
21
+ puts(output) unless ThinkingSphinx.suppress_delta_output?
22
+
23
+ client.update(
24
+ core_index_name(model),
25
+ ['sphinx_deleted'],
26
+ {instance.sphinx_document_id => [1]}
27
+ ) if instance && ThinkingSphinx.sphinx_running? && instance.in_both_indexes?
28
+
29
+ true
30
+ end
31
+
32
+ def toggle(instance)
33
+ instance.delta = true
34
+ end
35
+
36
+ def toggled(instance)
37
+ instance.delta
38
+ end
39
+
40
+ def reset_query(model)
41
+ "UPDATE #{model.quoted_table_name} SET " +
42
+ "#{model.connection.quote_column_name(@column.to_s)} = #{adapter.boolean(false)} " +
43
+ "WHERE #{model.connection.quote_column_name(@column.to_s)} = #{adapter.boolean(true)}"
44
+ end
45
+
46
+ def clause(model, toggled)
47
+ "#{model.quoted_table_name}.#{model.connection.quote_column_name(@column.to_s)}" +
48
+ " = #{adapter.boolean(toggled)}"
49
+ end
50
+
51
+ protected
52
+
53
+ def core_index_name(model)
54
+ "#{model.source_of_sphinx_index.name.underscore.tr(':/\\', '_')}_core"
55
+ end
56
+
57
+ def delta_index_name(model)
58
+ "#{model.source_of_sphinx_index.name.underscore.tr(':/\\', '_')}_delta"
59
+ end
60
+
61
+ private
62
+
63
+ def adapter
64
+ @adapter = @index.model.sphinx_database_adapter
65
+ end
66
+ end
67
+ end
68
+ end
@@ -0,0 +1,30 @@
1
+ require 'delayed/job'
2
+
3
+ require 'thinking_sphinx/deltas/delayed_delta/delta_job'
4
+ require 'thinking_sphinx/deltas/delayed_delta/flag_as_deleted_job'
5
+ require 'thinking_sphinx/deltas/delayed_delta/job'
6
+
7
+ module ThinkingSphinx
8
+ module Deltas
9
+ class DelayedDelta < ThinkingSphinx::Deltas::DefaultDelta
10
+ def index(model, instance = nil)
11
+ return true unless ThinkingSphinx.updates_enabled? && ThinkingSphinx.deltas_enabled?
12
+ return true if instance && !toggled(instance)
13
+
14
+ ThinkingSphinx::Deltas::Job.enqueue(
15
+ ThinkingSphinx::Deltas::DeltaJob.new(delta_index_name(model)),
16
+ ThinkingSphinx::Configuration.instance.delayed_job_priority
17
+ )
18
+
19
+ Delayed::Job.enqueue(
20
+ ThinkingSphinx::Deltas::FlagAsDeletedJob.new(
21
+ core_index_name(model), instance.sphinx_document_id
22
+ ),
23
+ ThinkingSphinx::Configuration.instance.delayed_job_priority
24
+ ) if instance
25
+
26
+ true
27
+ end
28
+ end
29
+ end
30
+ end
@@ -0,0 +1,24 @@
1
+ module ThinkingSphinx
2
+ module Deltas
3
+ class DeltaJob
4
+ attr_accessor :index
5
+
6
+ def initialize(index)
7
+ @index = index
8
+ end
9
+
10
+ def perform
11
+ return true unless ThinkingSphinx.updates_enabled? &&
12
+ ThinkingSphinx.deltas_enabled?
13
+
14
+ config = ThinkingSphinx::Configuration.instance
15
+ client = Riddle::Client.new config.address, config.port
16
+
17
+ output = `#{config.bin_path}#{config.indexer_binary_name} --config #{config.config_file} --rotate #{index}`
18
+ puts output unless ThinkingSphinx.suppress_delta_output?
19
+
20
+ true
21
+ end
22
+ end
23
+ end
24
+ end
@@ -0,0 +1,27 @@
1
+ module ThinkingSphinx
2
+ module Deltas
3
+ class FlagAsDeletedJob
4
+ attr_accessor :index, :document_id
5
+
6
+ def initialize(index, document_id)
7
+ @index, @document_id = index, document_id
8
+ end
9
+
10
+ def perform
11
+ return true unless ThinkingSphinx.updates_enabled?
12
+
13
+ config = ThinkingSphinx::Configuration.instance
14
+ client = Riddle::Client.new config.address, config.port
15
+
16
+ client.update(
17
+ @index,
18
+ ['sphinx_deleted'],
19
+ {@document_id => [1]}
20
+ ) if ThinkingSphinx.sphinx_running? &&
21
+ ThinkingSphinx::Search.search_for_id(@document_id, @index)
22
+
23
+ true
24
+ end
25
+ end
26
+ end
27
+ end
@@ -0,0 +1,26 @@
1
+ module ThinkingSphinx
2
+ module Deltas
3
+ class Job < Delayed::Job
4
+ def self.enqueue(object, priority = 0)
5
+ super unless duplicates_exist(object)
6
+ end
7
+
8
+ def self.cancel_thinking_sphinx_jobs
9
+ if connection.tables.include?("delayed_jobs")
10
+ delete_all("handler LIKE '--- !ruby/object:ThinkingSphinx::Deltas::%'")
11
+ end
12
+ end
13
+
14
+ private
15
+
16
+ def self.duplicates_exist(object)
17
+ count(
18
+ :conditions => {
19
+ :handler => object.to_yaml,
20
+ :locked_at => nil
21
+ }
22
+ ) > 0
23
+ end
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,100 @@
1
+ Capistrano::Configuration.instance(:must_exist).load do
2
+ namespace :thinking_sphinx do
3
+ namespace :install do
4
+ desc <<-DESC
5
+ Install Sphinx by source
6
+
7
+ If Postgres is available, Sphinx will use it.
8
+
9
+ If the variable :thinking_sphinx_configure_args is set, it will
10
+ be passed to the Sphinx configure script. You can use this to
11
+ install Sphinx in a non-standard location:
12
+
13
+ set :thinking_sphinx_configure_args, "--prefix=$HOME/software"
14
+ DESC
15
+
16
+ task :sphinx do
17
+ with_postgres = false
18
+ begin
19
+ run "which pg_config" do |channel, stream, data|
20
+ with_postgres = !(data.nil? || data == "")
21
+ end
22
+ rescue Capistrano::CommandError => e
23
+ puts "Continuing despite error: #{e.message}"
24
+ end
25
+
26
+ args = []
27
+ if with_postgres
28
+ run "pg_config --pkgincludedir" do |channel, stream, data|
29
+ args << "--with-pgsql=#{data}"
30
+ end
31
+ end
32
+ args << fetch(:thinking_sphinx_configure_args, '')
33
+
34
+ commands = <<-CMD
35
+ wget -q http://www.sphinxsearch.com/downloads/sphinx-0.9.8.1.tar.gz >> sphinx.log
36
+ tar xzvf sphinx-0.9.8.1.tar.gz
37
+ cd sphinx-0.9.8.1
38
+ ./configure #{args.join(" ")}
39
+ make
40
+ #{try_sudo} make install
41
+ rm -rf sphinx-0.9.8.1 sphinx-0.9.8.1.tar.gz
42
+ CMD
43
+ run commands.split(/\n\s+/).join(" && ")
44
+ end
45
+
46
+ desc "Install Thinking Sphinx as a gem from GitHub"
47
+ task :ts do
48
+ run "#{try_sudo} gem install thinking-sphinx --source http://gemcutter.org"
49
+ end
50
+ end
51
+
52
+ desc "Generate the Sphinx configuration file"
53
+ task :configure do
54
+ rake "thinking_sphinx:configure"
55
+ end
56
+
57
+ desc "Index data"
58
+ task :index do
59
+ rake "thinking_sphinx:index"
60
+ end
61
+
62
+ desc "Start the Sphinx daemon"
63
+ task :start do
64
+ configure
65
+ rake "thinking_sphinx:start"
66
+ end
67
+
68
+ desc "Stop the Sphinx daemon"
69
+ task :stop do
70
+ configure
71
+ rake "thinking_sphinx:stop"
72
+ end
73
+
74
+ desc "Stop and then start the Sphinx daemon"
75
+ task :restart do
76
+ stop
77
+ start
78
+ end
79
+
80
+ desc "Stop, re-index and then start the Sphinx daemon"
81
+ task :rebuild do
82
+ stop
83
+ index
84
+ start
85
+ end
86
+
87
+ desc "Add the shared folder for sphinx files for the production environment"
88
+ task :shared_sphinx_folder, :roles => :web do
89
+ run "mkdir -p #{shared_path}/db/sphinx/production"
90
+ end
91
+
92
+ def rake(*tasks)
93
+ rails_env = fetch(:rails_env, "production")
94
+ rake = fetch(:rake, "rake")
95
+ tasks.each do |t|
96
+ run "cd #{current_path}; #{rake} RAILS_ENV=#{rails_env} #{t}"
97
+ end
98
+ end
99
+ end
100
+ end
@@ -0,0 +1,22 @@
1
+ module ThinkingSphinx
2
+ class Excerpter
3
+ CoreMethods = %w( kind_of? object_id respond_to? should should_not stub! )
4
+ # Hide most methods, to allow them to be passed through to the instance.
5
+ instance_methods.select { |method|
6
+ method.to_s[/^__/].nil? && !CoreMethods.include?(method.to_s)
7
+ }.each { |method|
8
+ undef_method method
9
+ }
10
+
11
+ def initialize(search, instance)
12
+ @search = search
13
+ @instance = instance
14
+ end
15
+
16
+ def method_missing(method, *args, &block)
17
+ string = @instance.send(method, *args, &block).to_s
18
+
19
+ @search.excerpt_for(string, @instance.class)
20
+ end
21
+ end
22
+ end
@@ -0,0 +1,125 @@
1
+ module ThinkingSphinx
2
+ class Facet
3
+ attr_reader :property
4
+
5
+ def initialize(property)
6
+ @property = property
7
+
8
+ if property.columns.length != 1
9
+ raise "Can't translate Facets on multiple-column field or attribute"
10
+ end
11
+ end
12
+
13
+ def self.name_for(facet)
14
+ case facet
15
+ when Facet
16
+ facet.name
17
+ when String, Symbol
18
+ facet.to_s.gsub(/(_facet|_crc)$/,'').to_sym
19
+ end
20
+ end
21
+
22
+ def self.attribute_name_for(name)
23
+ name.to_s == 'class' ? 'class_crc' : "#{name}_facet"
24
+ end
25
+
26
+ def self.attribute_name_from_value(name, value)
27
+ case value
28
+ when String
29
+ attribute_name_for(name)
30
+ when Array
31
+ if value.all? { |val| val.is_a?(Integer) }
32
+ name
33
+ else
34
+ attribute_name_for(name)
35
+ end
36
+ else
37
+ name
38
+ end
39
+ end
40
+
41
+ def self.translate?(property)
42
+ return true if property.is_a?(Field)
43
+
44
+ case property.type
45
+ when :string
46
+ true
47
+ when :integer, :boolean, :datetime, :float
48
+ false
49
+ when :multi
50
+ !property.all_ints?
51
+ end
52
+ end
53
+
54
+ def name
55
+ property.unique_name
56
+ end
57
+
58
+ def attribute_name
59
+ if translate?
60
+ Facet.attribute_name_for(@property.unique_name)
61
+ else
62
+ @property.unique_name.to_s
63
+ end
64
+ end
65
+
66
+ def translate?
67
+ Facet.translate?(@property)
68
+ end
69
+
70
+ def type
71
+ @property.is_a?(Field) ? :string : @property.type
72
+ end
73
+
74
+ def value(object, attribute_value)
75
+ return translate(object, attribute_value) if translate? || float?
76
+
77
+ case @property.type
78
+ when :datetime
79
+ Time.at(attribute_value)
80
+ when :boolean
81
+ attribute_value > 0
82
+ else
83
+ attribute_value
84
+ end
85
+ end
86
+
87
+ def to_s
88
+ name
89
+ end
90
+
91
+ private
92
+
93
+ def translate(object, attribute_value)
94
+ objects = source_objects(object)
95
+ return nil if objects.nil? || objects.empty?
96
+
97
+ if objects.length > 1
98
+ objects.collect { |item| item.send(column.__name) }.detect { |item|
99
+ item.to_crc32 == attribute_value
100
+ }
101
+ else
102
+ objects.first.send(column.__name)
103
+ end
104
+ end
105
+
106
+ def source_objects(object)
107
+ column.__stack.each { |method|
108
+ object = Array(object).collect { |item|
109
+ item.send(method)
110
+ }.flatten.compact
111
+
112
+ return nil if object.empty?
113
+ }
114
+ Array(object)
115
+ end
116
+
117
+ def column
118
+ @property.columns.first
119
+ end
120
+
121
+ def float?
122
+ @property.type == :float
123
+ end
124
+ end
125
+ end