picky 4.21.0 → 4.21.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/picky/bundle.rb +3 -3
- data/lib/picky/category_indexing.rb +12 -2
- data/lib/picky/category_realtime.rb +10 -10
- data/lib/picky/helpers/indexing.rb +2 -2
- data/lib/picky/index.rb +4 -4
- data/lib/picky/index_indexing.rb +11 -0
- data/lib/picky/indexers/parallel.rb +5 -3
- data/spec/functional/id_spec.rb +66 -0
- data/spec/functional/terminate_early_spec.rb +11 -15
- data/spec/tools/picky/cli_spec.rb +1 -1
- metadata +5 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6c8689ff998ff025e835e1a5e6661ce766d51246
|
4
|
+
data.tar.gz: ae0fe1a7cfbd7bbf511fd049249d462bb683d955
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 602df847adb8be592eb798b261d41a22a530b09e8ea8a3b081a438b2153efef6320293a931e705a064e63b88a8b198fae891754999cd24da90d3923728cb2dbf
|
7
|
+
data.tar.gz: 1a98cf615c82128a6a107d4ec38ed747d5fc5a251318e167136cce36fb625ca814bacad6e15f60515e5e78781493378fd3dc53d5dff9e2e830829234b0f1c65d
|
data/lib/picky/bundle.rb
CHANGED
@@ -43,7 +43,7 @@ module Picky
|
|
43
43
|
|
44
44
|
forward :[], :[]=, :to => :configuration
|
45
45
|
forward :index_directory, :to => :category
|
46
|
-
|
46
|
+
|
47
47
|
# TODO Move the strategies into options.
|
48
48
|
#
|
49
49
|
def initialize name, category, weight_strategy, partial_strategy, similarity_strategy, options = {}
|
@@ -103,7 +103,7 @@ module Picky
|
|
103
103
|
def empty
|
104
104
|
on_all_indexes_call :empty
|
105
105
|
end
|
106
|
-
|
106
|
+
|
107
107
|
# Extracted to avoid duplicate code.
|
108
108
|
#
|
109
109
|
def on_all_indexes_call method_name
|
@@ -163,7 +163,7 @@ module Picky
|
|
163
163
|
def index_path type = nil
|
164
164
|
::File.join index_directory, "#{category.name}_#{name}#{ "_#{type}" if type }"
|
165
165
|
end
|
166
|
-
|
166
|
+
|
167
167
|
def to_tree_s indent = 0, &block
|
168
168
|
s = <<-TREE
|
169
169
|
#{' ' * indent}#{self.class.name.gsub('Picky::','')}(#{name})
|
@@ -73,7 +73,17 @@ module Picky
|
|
73
73
|
def key_format?
|
74
74
|
key_format
|
75
75
|
end
|
76
|
-
|
76
|
+
|
77
|
+
# Return the key format.
|
78
|
+
#
|
79
|
+
# If no key_format is defined on the category
|
80
|
+
# and the source has no key format, ask
|
81
|
+
# the index for one.
|
82
|
+
#
|
83
|
+
def id
|
84
|
+
@id ||= @index.id
|
85
|
+
end
|
86
|
+
|
77
87
|
def static?
|
78
88
|
@index.static? # || @static
|
79
89
|
end
|
@@ -83,7 +93,7 @@ module Picky
|
|
83
93
|
def from
|
84
94
|
@from || name
|
85
95
|
end
|
86
|
-
|
96
|
+
|
87
97
|
# Return an appropriate source.
|
88
98
|
#
|
89
99
|
# If we have no explicit source, we'll check the index for one.
|
@@ -1,7 +1,7 @@
|
|
1
1
|
module Picky
|
2
2
|
|
3
3
|
class Category
|
4
|
-
|
4
|
+
|
5
5
|
class Picky::IdNotGivenException < StandardError; end
|
6
6
|
|
7
7
|
# Removes an indexed object with the
|
@@ -20,9 +20,9 @@ module Picky
|
|
20
20
|
#
|
21
21
|
def add object, where = :unshift
|
22
22
|
if from.respond_to? :call
|
23
|
-
add_text object.id, from.call(object), where
|
23
|
+
add_text object.send(id), from.call(object), where
|
24
24
|
else
|
25
|
-
add_text object.id, object.send(from), where
|
25
|
+
add_text object.send(id), object.send(from), where
|
26
26
|
end
|
27
27
|
end
|
28
28
|
|
@@ -30,20 +30,20 @@ module Picky
|
|
30
30
|
# adds it again.
|
31
31
|
#
|
32
32
|
def replace object, where = :unshift
|
33
|
-
remove object.id
|
33
|
+
remove object.send id
|
34
34
|
add object, where
|
35
35
|
end
|
36
|
-
|
36
|
+
|
37
37
|
# Replaces just part of the indexed data.
|
38
38
|
#
|
39
39
|
# Note: Takes a hash as opposed to the add/replace method.
|
40
40
|
#
|
41
41
|
def replace_from hash #, id = (hash[:id] || hash['id'] || raise(IdNotGivenException.new)).send(key_format)
|
42
42
|
return unless text = hash[from] || hash[from.to_s]
|
43
|
-
|
43
|
+
|
44
44
|
raise IdNotGivenException.new unless id = hash[:id] || hash['id']
|
45
45
|
id = id.send key_format if key_format?
|
46
|
-
|
46
|
+
|
47
47
|
remove id
|
48
48
|
add_text id, text
|
49
49
|
end
|
@@ -71,13 +71,13 @@ module Picky
|
|
71
71
|
else
|
72
72
|
tokens = text_or_tokens
|
73
73
|
end
|
74
|
-
|
74
|
+
|
75
75
|
format = key_format?
|
76
76
|
tokens.each { |text| add_tokenized_token id, text, where, format }
|
77
77
|
rescue NoMethodError => e
|
78
78
|
show_informative_add_text_error_message_for e
|
79
79
|
end
|
80
|
-
|
80
|
+
|
81
81
|
def show_informative_add_text_error_message_for e
|
82
82
|
if e.name == :each
|
83
83
|
raise %Q{#{e.message}. You probably set tokenize: false on category "#{name}". It will need an Enumerator of previously tokenized tokens.}
|
@@ -90,7 +90,7 @@ module Picky
|
|
90
90
|
#
|
91
91
|
def add_tokenized_token id, text, where = :unshift, format = true, static = false
|
92
92
|
return unless text
|
93
|
-
|
93
|
+
|
94
94
|
id = id.send key_format if format
|
95
95
|
# text = text.to_sym if @symbols # SYMBOLS.
|
96
96
|
id.freeze
|
@@ -6,14 +6,14 @@ module Picky
|
|
6
6
|
module Indexing
|
7
7
|
|
8
8
|
include Measuring
|
9
|
-
|
9
|
+
|
10
10
|
# Runs the block and logs a few infos regarding the time it took.
|
11
11
|
#
|
12
12
|
def timed_indexing scheduler, &block
|
13
13
|
Picky.logger.info "Picky is indexing using #{scheduler.fork? ? 'multiple processes' : 'a single process'}: "
|
14
14
|
Picky.logger.info " Done in #{timed(&block).round}s.\n"
|
15
15
|
end
|
16
|
-
|
16
|
+
|
17
17
|
# Indexing works the same way, always:
|
18
18
|
# * Prepare the scheduler.
|
19
19
|
# * Cache the scheduler.
|
data/lib/picky/index.rb
CHANGED
@@ -126,7 +126,7 @@ module Picky
|
|
126
126
|
|
127
127
|
instance_eval(&Proc.new) if block_given?
|
128
128
|
end
|
129
|
-
|
129
|
+
|
130
130
|
# TODO Doc.
|
131
131
|
#
|
132
132
|
def static
|
@@ -149,7 +149,7 @@ module Picky
|
|
149
149
|
@backend ||= Backends::Memory.new
|
150
150
|
end
|
151
151
|
end
|
152
|
-
|
152
|
+
|
153
153
|
# The directory used by this index.
|
154
154
|
#
|
155
155
|
# Note: Used @directory ||=, but needs to be dynamic.
|
@@ -157,7 +157,7 @@ module Picky
|
|
157
157
|
def directory
|
158
158
|
::File.join(Picky.root, 'index', PICKY_ENVIRONMENT, name.to_s)
|
159
159
|
end
|
160
|
-
|
160
|
+
|
161
161
|
# Restrict categories to the given ones.
|
162
162
|
#
|
163
163
|
# Functionally equivalent as if indexes didn't
|
@@ -380,7 +380,7 @@ INDEX
|
|
380
380
|
].compact
|
381
381
|
"#{self.class}(#{s.join(', ')})"
|
382
382
|
end
|
383
|
-
|
383
|
+
|
384
384
|
# Displays the structure as a tree.
|
385
385
|
#
|
386
386
|
def to_tree_s indent = 0
|
data/lib/picky/index_indexing.rb
CHANGED
@@ -89,6 +89,17 @@ module Picky
|
|
89
89
|
@source.respond_to?(:call) ? @source.call : @source
|
90
90
|
end
|
91
91
|
|
92
|
+
# API method.
|
93
|
+
#
|
94
|
+
# Defines the name of the ID method to use on the indexed object.
|
95
|
+
#
|
96
|
+
# === Parameters
|
97
|
+
# * name: Method name of the ID.
|
98
|
+
#
|
99
|
+
def id name = nil
|
100
|
+
@id_name = name || @id_name || :id
|
101
|
+
end
|
102
|
+
|
92
103
|
# Define a key_format on the index.
|
93
104
|
#
|
94
105
|
# Parameter is a method name to use on the key (e.g. :to_i, :to_s, :strip, :split).
|
@@ -58,15 +58,17 @@ module Picky
|
|
58
58
|
def index_flush objects, file, category, cache, tokenizer
|
59
59
|
comma = ?,
|
60
60
|
newline = ?\n
|
61
|
-
|
61
|
+
|
62
62
|
# Optimized, therefore duplicate code.
|
63
63
|
#
|
64
|
+
id = category.id
|
65
|
+
from = category.from
|
64
66
|
objects.each do |object|
|
65
|
-
tokens = object.send
|
67
|
+
tokens = object.send from
|
66
68
|
tokens, _ = tokenizer.tokenize tokens if tokenizer # Note: Originals not needed. TODO Optimize?
|
67
69
|
tokens.each do |token_text|
|
68
70
|
next unless token_text
|
69
|
-
cache << object.id << comma << token_text << newline
|
71
|
+
cache << object.send(id) << comma << token_text << newline
|
70
72
|
end
|
71
73
|
end
|
72
74
|
|
@@ -0,0 +1,66 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
#
|
3
|
+
require 'spec_helper'
|
4
|
+
|
5
|
+
describe "id option" do
|
6
|
+
|
7
|
+
it 'can be given a different id (in-ruby based)' do
|
8
|
+
data = Picky::Index.new :id do
|
9
|
+
id :number
|
10
|
+
category :text
|
11
|
+
end
|
12
|
+
|
13
|
+
require 'ostruct'
|
14
|
+
|
15
|
+
thing = OpenStruct.new number: 1, text: "ohai"
|
16
|
+
other = OpenStruct.new number: 2, text: "ohai kthxbye"
|
17
|
+
|
18
|
+
data.add thing
|
19
|
+
data.add other
|
20
|
+
|
21
|
+
try = Picky::Search.new data
|
22
|
+
|
23
|
+
try.search("text:kthxbye").ids.should == [2]
|
24
|
+
end
|
25
|
+
|
26
|
+
it 'can be given a different id (source based)' do
|
27
|
+
require 'ostruct'
|
28
|
+
|
29
|
+
things = []
|
30
|
+
things << OpenStruct.new(number: 1, text: "ohai")
|
31
|
+
things << OpenStruct.new(number: 2, text: "ohai kthxbye")
|
32
|
+
|
33
|
+
data = Picky::Index.new :id do
|
34
|
+
source { things }
|
35
|
+
|
36
|
+
key_format :to_i
|
37
|
+
id :number # TODO :format => :to_i
|
38
|
+
category :text
|
39
|
+
end
|
40
|
+
|
41
|
+
data.index
|
42
|
+
|
43
|
+
try = Picky::Search.new data
|
44
|
+
|
45
|
+
try.search("text:kthxbye").ids.should == [2]
|
46
|
+
end
|
47
|
+
|
48
|
+
it 'default is id' do
|
49
|
+
index = Picky::Index.new :id do
|
50
|
+
category :text
|
51
|
+
end
|
52
|
+
|
53
|
+
require 'ostruct'
|
54
|
+
|
55
|
+
thing = OpenStruct.new id: 1, text: "ohai"
|
56
|
+
other = OpenStruct.new id: 2, text: "ohai kthxbye"
|
57
|
+
|
58
|
+
index.add thing
|
59
|
+
index.add other
|
60
|
+
|
61
|
+
try = Picky::Search.new index
|
62
|
+
|
63
|
+
try.search("text:kthxbye").ids.should == [2]
|
64
|
+
end
|
65
|
+
|
66
|
+
end
|
@@ -126,27 +126,23 @@ describe 'Search#terminate_early' do
|
|
126
126
|
try.search('hello', 1, 20).allocations.map(&:count).should == [6, 6, 6, 6]
|
127
127
|
try.search('hello', 1, 24).allocations.map(&:count).should == [6, 6, 6, 6]
|
128
128
|
|
129
|
-
try.search('hello', 1, 0).to_hash
|
130
|
-
|
129
|
+
result_hash = try.search('hello', 1, 0).to_hash
|
130
|
+
result_hash[:allocations].should == [
|
131
131
|
[:terminate_early, 1.792, 6, [[:text1, "hello", "hello"]], [6]],
|
132
132
|
[:terminate_early, 1.792, 6, [[:text2, "hello", "hello"]], []]
|
133
|
-
]
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
try.search('hello', 1, 12).to_hash.should == {
|
140
|
-
:allocations => [
|
133
|
+
]
|
134
|
+
result_hash[:offset].should == 0
|
135
|
+
result_hash[:total].should == 12
|
136
|
+
|
137
|
+
result_hash = try.search('hello', 1, 12).to_hash
|
138
|
+
result_hash[:allocations].should == [
|
141
139
|
[:terminate_early, 1.792, 6, [[:text1, "hello", "hello"]], []],
|
142
140
|
[:terminate_early, 1.792, 6, [[:text2, "hello", "hello"]], []],
|
143
141
|
[:terminate_early, 1.792, 6, [[:text3, "hello", "hello"]], [6]],
|
144
142
|
[:terminate_early, 1.792, 6, [[:text4, "hello", "hello"]], []]
|
145
|
-
]
|
146
|
-
|
147
|
-
|
148
|
-
:total => 24
|
149
|
-
}
|
143
|
+
]
|
144
|
+
result_hash[:offset].should == 12
|
145
|
+
result_hash[:total].should == 24
|
150
146
|
|
151
147
|
GC.start
|
152
148
|
|
@@ -4,7 +4,7 @@ require 'spec_helper'
|
|
4
4
|
|
5
5
|
# We need to load the CLI file explicitly as the CLI is not loaded with the Loader (not needed in the server, only for script runs).
|
6
6
|
#
|
7
|
-
require_relative '../../../
|
7
|
+
require_relative '../../../tools/picky/cli'
|
8
8
|
|
9
9
|
describe Picky::CLI do
|
10
10
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: picky
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 4.21.
|
4
|
+
version: 4.21.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Florian Hanke
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-05-
|
11
|
+
date: 2014-05-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|
@@ -243,6 +243,7 @@ files:
|
|
243
243
|
- spec/functional/exact_first_spec.rb
|
244
244
|
- spec/functional/facets_spec.rb
|
245
245
|
- spec/functional/from_spec.rb
|
246
|
+
- spec/functional/id_spec.rb
|
246
247
|
- spec/functional/ignore_allocations_spec.rb
|
247
248
|
- spec/functional/ignore_spec.rb
|
248
249
|
- spec/functional/max_allocations_spec.rb
|
@@ -397,7 +398,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
397
398
|
version: '0'
|
398
399
|
requirements: []
|
399
400
|
rubyforge_project: http://rubyforge.org/projects/picky
|
400
|
-
rubygems_version: 2.2.
|
401
|
+
rubygems_version: 2.2.2
|
401
402
|
signing_key:
|
402
403
|
specification_version: 4
|
403
404
|
summary: 'Picky: Semantic Search Engine. Clever Interface. Good Tools.'
|
@@ -421,6 +422,7 @@ test_files:
|
|
421
422
|
- spec/functional/exact_first_spec.rb
|
422
423
|
- spec/functional/facets_spec.rb
|
423
424
|
- spec/functional/from_spec.rb
|
425
|
+
- spec/functional/id_spec.rb
|
424
426
|
- spec/functional/ignore_allocations_spec.rb
|
425
427
|
- spec/functional/ignore_spec.rb
|
426
428
|
- spec/functional/max_allocations_spec.rb
|
@@ -553,4 +555,3 @@ test_files:
|
|
553
555
|
- spec/lib/tokenizer_spec.rb
|
554
556
|
- spec/performant_spec.rb
|
555
557
|
- spec/tools/picky/cli_spec.rb
|
556
|
-
has_rdoc:
|