picky 4.0.0pre1 → 4.0.0pre2

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 (112) hide show
  1. data/aux/picky/cli.rb +6 -2
  2. data/lib/picky.rb +10 -8
  3. data/lib/picky/backends/backend.rb +37 -0
  4. data/lib/picky/backends/file.rb +0 -20
  5. data/lib/picky/backends/memory.rb +0 -29
  6. data/lib/picky/backends/redis.rb +74 -15
  7. data/lib/picky/backends/redis/list.rb +1 -1
  8. data/lib/picky/backends/sqlite.rb +0 -27
  9. data/lib/picky/bundle.rb +2 -2
  10. data/lib/picky/bundle_indexed.rb +1 -1
  11. data/lib/picky/bundle_indexing.rb +1 -1
  12. data/lib/picky/categories_indexed.rb +1 -11
  13. data/lib/picky/category.rb +4 -4
  14. data/lib/picky/category/location.rb +25 -0
  15. data/lib/picky/category_realtime.rb +4 -3
  16. data/lib/picky/console.rb +1 -1
  17. data/lib/picky/constants.rb +1 -1
  18. data/lib/picky/ext/maybe_compile.rb +2 -2
  19. data/lib/picky/extensions/object.rb +3 -2
  20. data/lib/picky/generators/aliases.rb +7 -2
  21. data/lib/picky/generators/partial/default.rb +1 -0
  22. data/lib/picky/generators/similarity/default.rb +1 -0
  23. data/lib/picky/generators/similarity/phonetic.rb +13 -2
  24. data/lib/picky/generators/strategy.rb +0 -2
  25. data/lib/picky/generators/weights/constant.rb +1 -2
  26. data/lib/picky/generators/weights/default.rb +1 -0
  27. data/lib/picky/generators/weights/dynamic.rb +1 -1
  28. data/lib/picky/generators/weights/logarithmic.rb +1 -1
  29. data/lib/picky/generators/weights/{runtime.rb → stub.rb} +1 -3
  30. data/lib/picky/index.rb +3 -3
  31. data/lib/picky/index_indexing.rb +0 -2
  32. data/lib/picky/index_realtime.rb +1 -1
  33. data/lib/picky/indexers/base.rb +7 -0
  34. data/lib/picky/indexers/parallel.rb +2 -4
  35. data/lib/picky/indexers/serial.rb +2 -0
  36. data/lib/picky/indexes_indexing.rb +1 -1
  37. data/lib/picky/interfaces/live_parameters/master_child.rb +175 -0
  38. data/lib/picky/interfaces/live_parameters/unicorn.rb +37 -0
  39. data/lib/picky/loader.rb +238 -259
  40. data/lib/picky/query/allocation.rb +19 -10
  41. data/lib/picky/query/combination.rb +7 -1
  42. data/lib/picky/query/combinations.rb +1 -6
  43. data/lib/picky/query/token.rb +26 -36
  44. data/lib/picky/results.rb +18 -17
  45. data/lib/picky/scheduler.rb +2 -1
  46. data/lib/picky/search.rb +1 -1
  47. data/lib/picky/sinatra.rb +6 -6
  48. data/lib/picky/statistics.rb +2 -0
  49. data/lib/picky/tokenizer.rb +8 -8
  50. data/lib/picky/wrappers/bundle/calculation.rb +4 -4
  51. data/lib/picky/wrappers/bundle/location.rb +1 -2
  52. data/lib/tasks/framework.rake +1 -1
  53. data/lib/tasks/statistics.rake +1 -1
  54. data/lib/tasks/try.rake +1 -1
  55. data/lib/tasks/try.rb +1 -1
  56. data/spec/aux/picky/cli_spec.rb +12 -12
  57. data/spec/ext/performant_spec.rb +16 -16
  58. data/spec/functional/backends/file_spec.rb +78 -7
  59. data/spec/functional/backends/memory_spec.rb +78 -7
  60. data/spec/functional/backends/redis_spec.rb +73 -13
  61. data/spec/functional/dynamic_weights_spec.rb +3 -4
  62. data/spec/functional/realtime_spec.rb +2 -2
  63. data/spec/functional/speed_spec.rb +2 -2
  64. data/spec/functional/terminate_early_spec.rb +3 -3
  65. data/spec/lib/analytics_spec.rb +1 -1
  66. data/spec/lib/analyzer_spec.rb +5 -3
  67. data/spec/lib/categories_indexed_spec.rb +38 -20
  68. data/spec/lib/category/location_spec.rb +30 -0
  69. data/spec/lib/character_substituters/west_european_spec.rb +1 -0
  70. data/spec/lib/extensions/hash_spec.rb +6 -5
  71. data/spec/lib/extensions/module_spec.rb +6 -6
  72. data/spec/lib/extensions/object_spec.rb +9 -8
  73. data/spec/lib/extensions/string_spec.rb +1 -1
  74. data/spec/lib/generators/similarity/phonetic_spec.rb +11 -0
  75. data/spec/lib/index_realtime_spec.rb +5 -5
  76. data/spec/lib/interfaces/{live_parameters_spec.rb → live_parameters/master_child_spec.rb} +26 -26
  77. data/spec/lib/interfaces/live_parameters/unicorn_spec.rb +160 -0
  78. data/spec/lib/loader_spec.rb +65 -25
  79. data/spec/lib/query/allocation_spec.rb +25 -22
  80. data/spec/lib/query/combinations_spec.rb +13 -36
  81. data/spec/lib/query/token_spec.rb +144 -131
  82. data/spec/lib/query/tokens_spec.rb +14 -0
  83. data/spec/lib/results_spec.rb +14 -8
  84. data/spec/lib/search_spec.rb +1 -1
  85. data/spec/lib/sinatra_spec.rb +8 -8
  86. metadata +28 -91
  87. data/lib/picky/adapters/rack.rb +0 -34
  88. data/lib/picky/adapters/rack/base.rb +0 -27
  89. data/lib/picky/adapters/rack/live_parameters.rb +0 -37
  90. data/lib/picky/adapters/rack/search.rb +0 -67
  91. data/lib/picky/application.rb +0 -268
  92. data/lib/picky/frontend_adapters/rack.rb +0 -161
  93. data/lib/picky/interfaces/live_parameters.rb +0 -187
  94. data/lib/picky/sources/base.rb +0 -92
  95. data/lib/picky/sources/couch.rb +0 -76
  96. data/lib/picky/sources/csv.rb +0 -83
  97. data/lib/picky/sources/db.rb +0 -189
  98. data/lib/picky/sources/delicious.rb +0 -63
  99. data/lib/picky/sources/mongo.rb +0 -80
  100. data/lib/picky/wrappers/category/location.rb +0 -38
  101. data/lib/tasks/routes.rake +0 -8
  102. data/spec/lib/adapters/rack/base_spec.rb +0 -24
  103. data/spec/lib/adapters/rack/live_parameters_spec.rb +0 -26
  104. data/spec/lib/adapters/rack/query_spec.rb +0 -39
  105. data/spec/lib/application_spec.rb +0 -155
  106. data/spec/lib/frontend_adapters/rack_spec.rb +0 -294
  107. data/spec/lib/sources/base_spec.rb +0 -53
  108. data/spec/lib/sources/couch_spec.rb +0 -114
  109. data/spec/lib/sources/csv_spec.rb +0 -89
  110. data/spec/lib/sources/db_spec.rb +0 -125
  111. data/spec/lib/sources/delicious_spec.rb +0 -94
  112. data/spec/lib/sources/mongo_spec.rb +0 -50
@@ -1,53 +0,0 @@
1
- require 'spec_helper'
2
-
3
- describe Picky::Sources::Base do
4
- context 'with the base class' do
5
- let(:source) { described_class.new }
6
-
7
- describe 'connect_backend' do
8
- it 'exists' do
9
- source.connect_backend
10
- end
11
- end
12
-
13
- describe 'take_snapshot' do
14
- it 'exists and takes a single parameter' do
15
- source.take_snapshot :some_index
16
- end
17
- end
18
- end
19
-
20
- context 'with subclass' do
21
- let(:take_snapshot_called) { 0 }
22
- let(:subclass) do
23
- Class.new(described_class) do
24
- def take_snapshot index
25
- index.call index
26
- end
27
- end.new
28
- end
29
-
30
- describe 'with snapshot' do
31
- it 'is called only once when called in nested blocks' do
32
- index = stub :index, :identifier => :some_index
33
- subclass.stub! :timed_exclaim
34
-
35
- index.should_receive(:call).once.with index
36
-
37
- subclass.with_snapshot(index) do
38
- subclass.with_snapshot(index) do
39
- subclass.with_snapshot(index) do
40
-
41
- end
42
- end
43
- subclass.with_snapshot(index) do
44
- subclass.with_snapshot(index) do
45
-
46
- end
47
- end
48
- end
49
- end
50
- end
51
- end
52
-
53
- end
@@ -1,114 +0,0 @@
1
- require 'spec_helper'
2
-
3
- describe Picky::Sources::Couch do
4
-
5
- describe 'key_format' do
6
- context 'default' do
7
- let(:source) { described_class.new(:a, :b, url: 'bla') }
8
- it 'is correct' do
9
- source.key_format.should == :to_s
10
- end
11
- end
12
- context 'non-default' do
13
- let(:source) { described_class.new(:a, :b, url: 'bla', key_format: 'some_key_method') }
14
- it 'is correct' do
15
- source.key_format.should == :some_key_method
16
- end
17
- end
18
- end
19
-
20
- describe 'to_s' do
21
- let(:source) { described_class.new(:a, :b, :url => 'bla') }
22
- it 'is correct' do
23
- source.to_s.should == 'Picky::Sources::Couch'
24
- end
25
- end
26
-
27
- describe 'special keys' do
28
- context 'uuid keys' do
29
- context "with database" do
30
- before(:each) do
31
- @source = described_class.new :a, :b, :c, url: 'http://localhost:5984/picky'
32
- RestClient::Request.should_receive(:execute).any_number_of_times.and_return %{{"rows":[{"doc":{"_id":"550e8400-e29b-41d4-a716-446655440000","a":"a data","b":"b data","c":"c data"}}]}}
33
- end
34
-
35
- describe "harvest" do
36
- it "yields the right data" do
37
- category = stub :b, :from => :b
38
- @source.harvest category do |id, token|
39
- id.should eql('550e8400-e29b-41d4-a716-446655440000')
40
- token.should eql('b data')
41
- end.should have(1).item
42
- end
43
- end
44
-
45
- describe "get_data" do
46
- it "yields each line" do
47
- @source.get_data do |data|
48
- data.should == { "_id" => "550e8400-e29b-41d4-a716-446655440000", "a" => "a data", "b" => "b data", "c" => "c data" }
49
- end.should have(1).item
50
- end
51
- end
52
- end
53
- end
54
- context 'integer keys' do
55
- context "with database" do
56
- before(:each) do
57
- @source = described_class.new :a, :b, :c, url: 'http://localhost:5984/picky'
58
- RestClient::Request.should_receive(:execute).any_number_of_times.and_return %{{"rows":[{"doc":{"_id":"123","a":"a data","b":"b data","c":"c data"}}]}}
59
- end
60
-
61
- describe "harvest" do
62
- it "yields the right data" do
63
- category = stub :b, :from => :b
64
- @source.harvest category do |id, token|
65
- id.should eql('123')
66
- token.should eql('b data')
67
- end.should have(1).item
68
- end
69
- end
70
-
71
- describe "get_data" do
72
- it "yields each line" do
73
- @source.get_data do |data|
74
- data.should == { "_id" => "123", "a" => "a data", "b" => "b data", "c" => "c data" }
75
- end.should have(1).item
76
- end
77
- end
78
- end
79
- end
80
- end
81
-
82
- context 'default keys' do
83
- context "without database" do
84
- it "should fail correctly" do
85
- lambda { described_class.new(:a, :b, :c) }.should raise_error(described_class::NoDBGiven)
86
- end
87
- end
88
-
89
- context "with database" do
90
- before(:each) do
91
- @source = described_class.new :a, :b, :c, url: 'http://localhost:5984/picky'
92
- RestClient::Request.should_receive(:execute).any_number_of_times.and_return %{{"rows":[{"doc":{"_id":"7f","a":"a data","b":"b data","c":"c data"}}]}}
93
- end
94
-
95
- describe "harvest" do
96
- it "yields the right data" do
97
- category = stub :b, :from => :b
98
- @source.harvest category do |id, token|
99
- id.should eql('7f')
100
- token.should eql('b data')
101
- end.should have(1).item
102
- end
103
- end
104
-
105
- describe "get_data" do
106
- it "yields each line" do
107
- @source.get_data do |data|
108
- data.should == { "_id" => "7f", "a" => "a data", "b" => "b data", "c" => "c data" }
109
- end.should have(1).item
110
- end
111
- end
112
- end
113
- end
114
- end
@@ -1,89 +0,0 @@
1
- require 'spec_helper'
2
- require 'csv'
3
-
4
- describe Picky::Sources::CSV do
5
-
6
- describe 'to_s' do
7
- let(:source) { described_class.new :a, :b, :c, file:'some/file.csv' }
8
- it 'outputs the correct string' do
9
- source.to_s.should == 'Picky::Sources::CSV(a, b, c, {:file=>"some/file.csv"})'
10
- end
11
- end
12
-
13
- describe 'without separator' do
14
- before(:each) do
15
- @source = described_class.new :a, :b, :c, :file => :some_file
16
- end
17
- it 'calls foreach correctly' do
18
- block = lambda { |*args| }
19
-
20
- ::CSV.should_receive(:foreach).once.with :some_file, {}, &block
21
-
22
- @source.get_data &block
23
- end
24
- end
25
- describe 'with separator' do
26
- before(:each) do
27
- @source = described_class.new :a, :b, :c, :file => :some_file, :col_sep => 'some_separator'
28
- end
29
- it 'calls foreach correctly' do
30
- block = lambda { |*args| }
31
-
32
- ::CSV.should_receive(:foreach).once.with :some_file, :col_sep => 'some_separator', &block
33
-
34
- @source.get_data &block
35
- end
36
- end
37
-
38
- context "without file" do
39
- it "should fail correctly" do
40
- lambda { @source = described_class.new(:a, :b, :c) }.should raise_error(described_class::NoFileGiven)
41
- end
42
- end
43
- context "with file" do
44
- before(:each) do
45
- ::CSV.should_receive(:foreach).any_number_of_times.and_yield [' 7', 'a data', 'b data', 'c data']
46
- end
47
- context 'without separator' do
48
- before(:each) do
49
- @source = described_class.new :a, :b, :c, :file => :some_file
50
- end
51
- describe "harvest" do
52
- it "should yield the right data" do
53
- category = stub :b, :from => :b
54
- @source.harvest category do |id, token|
55
- [id, token].should == [' 7', 'b data']
56
- end
57
- end
58
- end
59
- describe "get_data" do
60
- it "should yield each line" do
61
- @source.get_data do |data|
62
- data.should == [' 7', 'a data', 'b data', 'c data']
63
- end
64
- end
65
- end
66
- end
67
- context 'with key_format method' do
68
- before(:each) do
69
- @source = described_class.new :a, :b, :c, :file => :some_file, :key_format => :strip
70
- end
71
- describe "harvest" do
72
- it "should yield the right data" do
73
- category = stub :b, :from => :b
74
- @source.harvest category do |id, token|
75
- [id, token].should == [' 7', 'b data']
76
- end
77
- end
78
- end
79
- describe "get_data" do
80
- it "should yield each line" do
81
- @source.get_data do |data|
82
- data.should == [' 7', 'a data', 'b data', 'c data']
83
- end
84
- end
85
- end
86
- end
87
- end
88
-
89
- end
@@ -1,125 +0,0 @@
1
- require 'spec_helper'
2
-
3
- describe Picky::Sources::DB do
4
-
5
- before(:each) do
6
- @connection = stub :connection
7
- @adapter = stub :adapter, :connection => @connection
8
-
9
- @select_statement = stub :statement, :inspect => '"some statement"'
10
-
11
- @source = described_class.new @select_statement, :option => :some_options
12
-
13
- @source.stub! :database => @adapter
14
- @source.stub! :connect_backend
15
- end
16
-
17
- describe 'to_s' do
18
- it 'does something' do
19
- @source.to_s.should == 'Picky::Sources::DB("some statement", {:option=>:some_options})'
20
- end
21
- end
22
-
23
- describe "get_data" do
24
- before(:each) do
25
- @category = stub :category, :from => :some_category, :index_name => :some_index_name
26
- end
27
- context 'mysql' do
28
- before(:each) do
29
- @connection.stub! :adapter_name => 'mysql'
30
- end
31
- context 'no data' do
32
- it "delegates to the connection" do
33
-
34
- @connection.should_receive(:execute).
35
- once.
36
- with('SELECT id, some_category FROM picky_some_index_name_index st WHERE st.__picky_id > some_offset LIMIT 25000').
37
- and_return []
38
-
39
- @source.get_data @category, :some_offset
40
- end
41
- end
42
- context 'with data' do
43
- it 'yields to the caller' do
44
- @connection.should_receive(:execute).
45
- any_number_of_times.
46
- with('SELECT id, some_category FROM picky_some_index_name_index st WHERE st.__picky_id > some_offset LIMIT 25000').
47
- and_return [[1, 'text']]
48
-
49
- @source.get_data @category, :some_offset do |id, text|
50
- id.should == 1
51
- text.should == 'text'
52
- end
53
- end
54
- end
55
- end
56
- end
57
-
58
- describe "configure" do
59
- it "works" do
60
- lambda { @source.configure({}) }.should_not raise_error
61
- end
62
- context "with file" do
63
- it "opens the config file relative to root" do
64
- File.should_receive(:open).once.with 'spec/test_directory/app/bla.yml'
65
-
66
- @source.configure :file => 'app/bla.yml'
67
- end
68
- end
69
- end
70
-
71
- describe "connect_backend" do
72
- it "works" do
73
- lambda { @source.connect_backend }.should_not raise_error
74
- end
75
- end
76
-
77
- describe "chunksize" do
78
- it "should be a specific size" do
79
- @source.chunksize.should == 25_000
80
- end
81
- end
82
-
83
- describe "count" do
84
- it "should get the count through the public DB connection" do
85
- result = stub(:result, :to_i => 12_345)
86
- @connection.should_receive(:select_value).once.and_return(result)
87
-
88
- @source.count :anything
89
- end
90
- it "should get the id count" do
91
- result = stub(:result, :to_i => 12_345)
92
- @connection.should_receive(:select_value).once.with("SELECT COUNT(__picky_id) FROM picky_some_type_name_index")
93
-
94
- @source.count :some_type_name
95
- end
96
- end
97
-
98
- describe 'harvest' do
99
- before(:each) do
100
- @category = stub :category, :name => :some_category, :index_name => :some_index
101
-
102
- @source.should_receive(:get_data).any_number_of_times.and_return [[:some_id, 'some_text']].cycle
103
- @source.stub! :count => 17
104
- end
105
- end
106
-
107
- describe "harvest_statement_with_offset" do
108
- before(:each) do
109
- @category = stub :category, :from => :some_category
110
- end
111
- it "should get a harvest statement and the chunksize to put the statement together" do
112
- @source.should_receive(:harvest_statement).once.with(@category).and_return 'some_example_statement'
113
- @source.harvest_statement_with_offset(@category, :some_offset)
114
- end
115
- it "should add an AND if it already contains a WHERE statement" do
116
- @source.should_receive(:harvest_statement).and_return 'WHERE'
117
- @source.harvest_statement_with_offset(@category, :some_offset).should == "WHERE AND st.__picky_id > some_offset LIMIT 25000"
118
- end
119
- it "should add a WHERE if it doesn't already contain one" do
120
- @source.should_receive(:harvest_statement).and_return 'some_statement'
121
- @source.harvest_statement_with_offset(@category, :some_offset).should == "some_statement WHERE st.__picky_id > some_offset LIMIT 25000"
122
- end
123
- end
124
-
125
- end
@@ -1,94 +0,0 @@
1
- require 'spec_helper'
2
-
3
- describe Picky::Sources::Delicious do
4
-
5
- context "with file" do
6
-
7
- describe 'to_s' do
8
- it 'outputs correctly' do
9
- described_class.new(:username, :password).to_s.should == 'Picky::Sources::Delicious(username)'
10
- end
11
- end
12
-
13
- describe "check_gem" do
14
- before(:each) do
15
- @source = described_class.allocate
16
- end
17
- context "doesn't find www/delicious" do
18
- before(:each) do
19
- @source.should_receive(:require).any_number_of_times.and_raise LoadError
20
- end
21
- it "warns & exits" do
22
- @source.should_receive(:warn).once.with "www-delicious gem missing!\nTo use the delicious source, you need to:\n 1. Add the following line to Gemfile:\n gem 'www-delicious'\n or\n require 'www-delicious'\n for example on top of your app.rb/application.rb\n 2. Then, run:\n bundle update\n"
23
- @source.should_receive(:exit).once.with 1
24
-
25
- @source.check_gem
26
- end
27
- end
28
- context "finds www/delicious" do
29
- before(:each) do
30
- @source.should_receive(:require).any_number_of_times.and_return
31
- end
32
- it "checks if the gem is there" do
33
- lambda { @source.check_gem }.should_not raise_error
34
- end
35
- end
36
- end
37
-
38
- describe "harvest" do
39
- before(:each) do
40
- @source = described_class.new(:username, :password)
41
-
42
- post1 = WWW::Delicious::Post.new
43
- post1.uid = "5045d67b3f251e4ae966dffe71501763"
44
- post1.tags = ["barefoot", "running", "shoe"]
45
- post1.title = "VIBRAM - FiveFingers"
46
- post1.url = URI.parse('http://www.vibramfivefingers.it/')
47
-
48
- delicious = stub :delicious, :posts_recent => [post1]
49
-
50
- WWW::Delicious.should_receive(:new).and_return delicious
51
- end
52
- it "should yield the right data" do
53
- category = stub :b, :from => :tags
54
- @source.harvest category do |id, token|
55
- [id, token].should == [1, "barefoot running shoe"]
56
- end
57
- end
58
- it "should yield the right data" do
59
- category = stub :b, :from => :title
60
- @source.harvest category do |id, token|
61
- [id, token].should == [1, "VIBRAM - FiveFingers"]
62
- end
63
- end
64
- it "should yield the right data" do
65
- category = stub :b, :from => :url
66
- @source.harvest category do |id, token|
67
- [id, token].should == [1, "http://www.vibramfivefingers.it/"]
68
- end
69
- end
70
- end
71
- describe "get_data" do
72
- before(:each) do
73
- @source = described_class.new(:username, :password)
74
-
75
- post1 = WWW::Delicious::Post.new
76
- post1.uid = "5045d67b3f251e4ae966dffe71501763"
77
- post1.tags = ["barefoot", "running", "shoe"]
78
- post1.title = "VIBRAM - FiveFingers"
79
- post1.url = URI.parse('http://www.vibramfivefingers.it/')
80
-
81
- delicious = stub :delicious, :posts_recent => [post1]
82
-
83
- WWW::Delicious.should_receive(:new).and_return delicious
84
- end
85
- it "should yield each line" do
86
- @source.get_data do |uid, data|
87
- uid.should == 1
88
- data.should == { :title => "VIBRAM - FiveFingers", :tags => "barefoot running shoe", :url => "http://www.vibramfivefingers.it/" }
89
- end
90
- end
91
- end
92
- end
93
-
94
- end