picky 4.0.0pre5 → 4.0.0pre6
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/picky/analyzer.rb +9 -7
- data/lib/picky/backends/file/json.rb +6 -0
- data/lib/picky/backends/redis/list.rb +9 -0
- data/lib/picky/backends/redis/string.rb +6 -0
- data/lib/picky/backends/sqlite/array.rb +5 -0
- data/lib/picky/bundle.rb +1 -6
- data/lib/picky/bundle_indexed.rb +1 -3
- data/lib/picky/bundle_realtime.rb +2 -0
- data/lib/picky/category.rb +6 -3
- data/lib/picky/generators/similarity/phonetic.rb +2 -4
- data/lib/picky/interfaces/live_parameters/master_child.rb +2 -1
- data/spec/lib/bundle_indexing_spec.rb +1 -1
- data/spec/lib/generators/similarity/phonetic_spec.rb +15 -7
- metadata +17 -17
data/lib/picky/analyzer.rb
CHANGED
@@ -40,6 +40,7 @@ class Analyzer # :nodoc:all
|
|
40
40
|
end
|
41
41
|
def cardinality identifier, index
|
42
42
|
return if index.size.zero?
|
43
|
+
return unless index.respond_to?(:each_pair)
|
43
44
|
|
44
45
|
key_length_average = 0
|
45
46
|
ids_length_average = 0
|
@@ -49,7 +50,7 @@ class Analyzer # :nodoc:all
|
|
49
50
|
min_key_length = 1.0/0 # Infinity
|
50
51
|
max_key_length = 0
|
51
52
|
|
52
|
-
key_size, ids_size =
|
53
|
+
key_size, ids_size = 0, 0
|
53
54
|
index.each_pair do |key, ids|
|
54
55
|
key_size = key.size
|
55
56
|
if key_size < min_key_length
|
@@ -91,7 +92,8 @@ class Analyzer # :nodoc:all
|
|
91
92
|
end
|
92
93
|
end
|
93
94
|
def weights index
|
94
|
-
return if index.size.zero?
|
95
|
+
return if !index.respond_to?(:size) || index.size.zero?
|
96
|
+
return unless index.respond_to?(:each_pair)
|
95
97
|
|
96
98
|
min_weight = 1.0/0 # Infinity
|
97
99
|
max_weight = 0.0
|
@@ -131,11 +133,11 @@ class Analyzer # :nodoc:all
|
|
131
133
|
end
|
132
134
|
def index_to_s
|
133
135
|
return if analysis[:__keys].zero?
|
134
|
-
[
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
136
|
+
ary = ["index key cardinality: #{"%10d" % analysis[:__keys]}"]
|
137
|
+
return ary.join "\n" unless analysis[:index]
|
138
|
+
ary << "index key length range (avg): #{"%10s" % analysis[:index][:key_length]} (#{analysis[:index][:key_length_average].round(2)})"
|
139
|
+
ary << "index ids per key length range (avg): #{"%10s" % analysis[:index][:ids_length]} (#{analysis[:index][:ids_length_average].round(2)})"
|
140
|
+
ary.join "\n"
|
139
141
|
end
|
140
142
|
def weights_to_s
|
141
143
|
return unless analysis[:weights]
|
@@ -18,6 +18,15 @@ module Picky
|
|
18
18
|
end
|
19
19
|
end
|
20
20
|
|
21
|
+
# Size of the list(s).
|
22
|
+
#
|
23
|
+
def size
|
24
|
+
redis_key = "#{namespace}:*"
|
25
|
+
client.keys(redis_key).inject(0) do |total, key|
|
26
|
+
total + client.zcard(key)
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
21
30
|
# Deletes the list for the key.
|
22
31
|
#
|
23
32
|
def delete key
|
@@ -10,6 +10,11 @@ module Picky
|
|
10
10
|
db.execute 'create table key_value (key varchar(255), value text);'
|
11
11
|
end
|
12
12
|
|
13
|
+
def size
|
14
|
+
result = db.execute 'SELECT COUNT(*) FROM key_value'
|
15
|
+
result.first.first.to_i
|
16
|
+
end
|
17
|
+
|
13
18
|
def []= key, array
|
14
19
|
unless array.empty?
|
15
20
|
db.execute 'INSERT OR REPLACE INTO key_value (key,value) VALUES (?,?)',
|
data/lib/picky/bundle.rb
CHANGED
@@ -91,11 +91,8 @@ module Picky
|
|
91
91
|
# the strategy itself pretends to be an index.
|
92
92
|
#
|
93
93
|
def initialize_backends
|
94
|
-
# @inverted, @weights, @similarity, @configuration, @realtime = backend.initial weight_strategy
|
95
94
|
@inverted = @backend_inverted.initial
|
96
|
-
|
97
|
-
#
|
98
|
-
@weights = @weight_strategy.saved?? @backend_weights.initial : @weight_strategy
|
95
|
+
@weights = @weight_strategy.saved? ? @backend_weights.initial : @weight_strategy
|
99
96
|
@similarity = @backend_similarity.initial
|
100
97
|
@configuration = @backend_configuration.initial
|
101
98
|
@realtime = @backend_realtime.initial
|
@@ -106,8 +103,6 @@ module Picky
|
|
106
103
|
#
|
107
104
|
def empty
|
108
105
|
@inverted = @backend_inverted.empty
|
109
|
-
# THINK about this. Perhaps the strategies should implement the backend methods?
|
110
|
-
#
|
111
106
|
@weights = @weight_strategy.saved? ? @backend_weights.empty : @weight_strategy
|
112
107
|
@similarity = @backend_similarity.empty
|
113
108
|
@configuration = @backend_configuration.empty
|
data/lib/picky/bundle_indexed.rb
CHANGED
@@ -25,7 +25,7 @@ module Picky
|
|
25
25
|
#
|
26
26
|
def ids sym_or_string
|
27
27
|
@inverted[sym_or_string] || []
|
28
|
-
#
|
28
|
+
# THINK Place the key_format conversion here – or move into the backend?
|
29
29
|
#
|
30
30
|
# if @key_format
|
31
31
|
# class << self
|
@@ -79,8 +79,6 @@ module Picky
|
|
79
79
|
# Loads the weights index.
|
80
80
|
#
|
81
81
|
def load_weights
|
82
|
-
# TODO @weights = @weight_strategy.load || @backend_weights.load
|
83
|
-
#
|
84
82
|
self.weights = @backend_weights.load if @weight_strategy.saved?
|
85
83
|
end
|
86
84
|
# Loads the similarity index.
|
data/lib/picky/category.rb
CHANGED
@@ -16,13 +16,16 @@ module Picky
|
|
16
16
|
# * partial: Partial::None.new, Partial::Substring.new(from:start_char, to:up_to_char) (defaults from:-3, to:-1)
|
17
17
|
# * similarity: Similarity::None.new (default), Similarity::DoubleMetaphone.new(amount_of_similarly_linked_words)
|
18
18
|
# * from: The source category identifier to take the data from.
|
19
|
+
# * key_format: What this category's keys are formatted with (default is :to_i)
|
20
|
+
# * backend: The backend to use. Default is Backends::Memory.new.
|
21
|
+
# Other options are: Backends::Redis.new, Backends::SQLite.new, Backends::File.new.
|
22
|
+
# * qualifiers: Which qualifiers can be used to predefine the category. E.g. "title:bla".
|
19
23
|
#
|
20
24
|
# Advanced Options:
|
21
|
-
# *
|
22
|
-
# * weights: Query::Weights.new( [:category1, :category2] => +2, ... )
|
25
|
+
# * weight: Query::Weights.new( [:category1, :category2] => +2, ... )
|
23
26
|
# * tokenizer: Use a subclass of Tokenizers::Base that implements #tokens_for and #empty_tokens.
|
24
|
-
# * key_format: What this category's keys are formatted with (default is :to_i)
|
25
27
|
# * use_symbols: Whether to use symbols internally instead of strings.
|
28
|
+
# * source: Use if the category should use a different source.
|
26
29
|
#
|
27
30
|
def initialize name, index, options = {}
|
28
31
|
@name = name
|
@@ -36,11 +36,9 @@ module Picky
|
|
36
36
|
|
37
37
|
# Sorts the index values in place.
|
38
38
|
#
|
39
|
-
|
40
|
-
#
|
41
|
-
def prioritize! ary, code
|
39
|
+
def prioritize ary, code
|
42
40
|
ary.sort_by_levenshtein! code
|
43
|
-
ary.slice! amount, ary.size #
|
41
|
+
ary.slice! amount, ary.size # Note: The ary.size is not perfectly correct.
|
44
42
|
end
|
45
43
|
|
46
44
|
end
|
@@ -130,7 +130,8 @@ module Picky
|
|
130
130
|
}
|
131
131
|
end
|
132
132
|
|
133
|
-
#
|
133
|
+
# THINK What to do about this? Standardize the tokenizer interface,
|
134
|
+
# then access each individual tokenizer.
|
134
135
|
#
|
135
136
|
def querying_removes_characters
|
136
137
|
regexp = Tokenizer.searching.instance_variable_get :@removes_characters_regexp
|
@@ -25,7 +25,7 @@ describe Picky::Bundle do
|
|
25
25
|
bundle.similar(:dragon).should == [:dargon]
|
26
26
|
end
|
27
27
|
it 'returns the right similars' do
|
28
|
-
bundle.similar(:trkn).should == [:
|
28
|
+
bundle.similar(:trkn).should == [:dargon, :dragon]
|
29
29
|
end
|
30
30
|
it 'performs' do
|
31
31
|
performance_of { bundle.similar(:dragon) }.should < 0.000075
|
@@ -21,13 +21,13 @@ describe Picky::Generators::Similarity::Phonetic do
|
|
21
21
|
instance.send :initialize
|
22
22
|
end
|
23
23
|
|
24
|
-
describe 'prioritize
|
24
|
+
describe 'prioritize' do
|
25
25
|
let(:phonetic) { described_class.allocate }
|
26
26
|
it 'sorts correctly' do
|
27
27
|
phonetic.instance_variable_set :@amount, 2
|
28
28
|
|
29
29
|
ary = [:a, :b, :c]
|
30
|
-
phonetic.prioritize
|
30
|
+
phonetic.prioritize ary, :b
|
31
31
|
|
32
32
|
ary.should == [:b, :a]
|
33
33
|
end
|
@@ -35,7 +35,7 @@ describe Picky::Generators::Similarity::Phonetic do
|
|
35
35
|
phonetic.instance_variable_set :@amount, 2
|
36
36
|
|
37
37
|
ary = [:aaa, :aa, :aaaa]
|
38
|
-
phonetic.prioritize
|
38
|
+
phonetic.prioritize ary, :aaa
|
39
39
|
|
40
40
|
ary.should == [:aaa, :aa]
|
41
41
|
end
|
@@ -43,7 +43,7 @@ describe Picky::Generators::Similarity::Phonetic do
|
|
43
43
|
phonetic.instance_variable_set :@amount, 3
|
44
44
|
|
45
45
|
ary = [:aaa, :aa, :aaaa]
|
46
|
-
phonetic.prioritize
|
46
|
+
phonetic.prioritize ary, :aaa
|
47
47
|
|
48
48
|
ary.should == [:aaa, :aa, :aaaa]
|
49
49
|
end
|
@@ -51,7 +51,7 @@ describe Picky::Generators::Similarity::Phonetic do
|
|
51
51
|
phonetic.instance_variable_set :@amount, 3
|
52
52
|
|
53
53
|
ary = [:aaaaa, :aa, :aaaa]
|
54
|
-
phonetic.prioritize
|
54
|
+
phonetic.prioritize ary, :aaa
|
55
55
|
|
56
56
|
ary.should == [:aaaa, :aa, :aaaaa]
|
57
57
|
end
|
@@ -59,7 +59,7 @@ describe Picky::Generators::Similarity::Phonetic do
|
|
59
59
|
phonetic.instance_variable_set :@amount, 3
|
60
60
|
|
61
61
|
ary = [:aaaaa, :aa]
|
62
|
-
phonetic.prioritize
|
62
|
+
phonetic.prioritize ary, :aaa
|
63
63
|
|
64
64
|
ary.should == [:aa, :aaaaa]
|
65
65
|
end
|
@@ -67,7 +67,15 @@ describe Picky::Generators::Similarity::Phonetic do
|
|
67
67
|
phonetic.instance_variable_set :@amount, 3
|
68
68
|
|
69
69
|
ary = [:aaa]
|
70
|
-
phonetic.prioritize
|
70
|
+
phonetic.prioritize ary, :aaa
|
71
|
+
|
72
|
+
ary.should == [:aaa]
|
73
|
+
end
|
74
|
+
it 'sorts correctly' do
|
75
|
+
phonetic.instance_variable_set :@amount, 1
|
76
|
+
|
77
|
+
ary = [:a, :aa, :aaa]
|
78
|
+
phonetic.prioritize ary, :aaa
|
71
79
|
|
72
80
|
ary.should == [:aaa]
|
73
81
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: picky
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 4.0.
|
4
|
+
version: 4.0.0pre6
|
5
5
|
prerelease: 5
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2011-12-
|
12
|
+
date: 2011-12-16 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: rspec
|
16
|
-
requirement: &
|
16
|
+
requirement: &70149986589980 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,21 +21,21 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :development
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *70149986589980
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: picky-client
|
27
|
-
requirement: &
|
27
|
+
requirement: &70149986589080 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ~>
|
31
31
|
- !ruby/object:Gem::Version
|
32
|
-
version: 4.0.
|
32
|
+
version: 4.0.0pre6
|
33
33
|
type: :development
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *70149986589080
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: text
|
38
|
-
requirement: &
|
38
|
+
requirement: &70149986588600 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>='
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0'
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *70149986588600
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: yajl-ruby
|
49
|
-
requirement: &
|
49
|
+
requirement: &70149986588080 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :runtime
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *70149986588080
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: activesupport
|
60
|
-
requirement: &
|
60
|
+
requirement: &70149986587440 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: '3.0'
|
66
66
|
type: :runtime
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *70149986587440
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: procrastinate
|
71
|
-
requirement: &
|
71
|
+
requirement: &70149986602940 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ~>
|
@@ -76,10 +76,10 @@ dependencies:
|
|
76
76
|
version: '0.4'
|
77
77
|
type: :runtime
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *70149986602940
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: rack_fast_escape
|
82
|
-
requirement: &
|
82
|
+
requirement: &70149986602420 !ruby/object:Gem::Requirement
|
83
83
|
none: false
|
84
84
|
requirements:
|
85
85
|
- - ! '>='
|
@@ -87,7 +87,7 @@ dependencies:
|
|
87
87
|
version: '0'
|
88
88
|
type: :runtime
|
89
89
|
prerelease: false
|
90
|
-
version_requirements: *
|
90
|
+
version_requirements: *70149986602420
|
91
91
|
description: Fast Ruby semantic text search engine with comfortable single field interface.
|
92
92
|
email: florian.hanke+picky@gmail.com
|
93
93
|
executables:
|