model_iterator 1.0.1 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +11 -7
- data/lib/model_iterator.rb +12 -5
- data/model_iterator.gemspec +4 -2
- data/script/bootstrap +6 -0
- data/script/test +5 -0
- data/test/init_test.rb +75 -0
- data/test/iterate_test.rb +24 -0
- metadata +5 -3
data/README.md
CHANGED
@@ -4,17 +4,21 @@ Basic library for iterating through large ActiveRecord datasets. For instance,
|
|
4
4
|
let's say you add a new feature, and you need to backfill data for existing
|
5
5
|
records:
|
6
6
|
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
7
|
+
```ruby
|
8
|
+
iter = ModelIterator.new(User, :redis => $redis)
|
9
|
+
iter.each do |user|
|
10
|
+
backfill(user)
|
11
|
+
end
|
12
|
+
```
|
11
13
|
|
12
14
|
ModelIterator selects the records in batches (100 by default), and loops
|
13
15
|
through the table filtering based on the ID.
|
14
16
|
|
15
|
-
|
16
|
-
|
17
|
-
|
17
|
+
```sql
|
18
|
+
SELECT * FROM users WHERE id > 0 LIMIT 100
|
19
|
+
SELECT * FROM users WHERE id > 100 LIMIT 100
|
20
|
+
SELECT * FROM users WHERE id > 200 LIMIT 100
|
21
|
+
```
|
18
22
|
|
19
23
|
Each record's ID is tracked in Redis immediately after being processed. If
|
20
24
|
jobs crash, you can fix code, and re-run from where you left off.
|
data/lib/model_iterator.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# Iterates over large models, storing state in Redis.
|
2
2
|
class ModelIterator
|
3
|
-
VERSION = "1.0.
|
3
|
+
VERSION = "1.0.2"
|
4
4
|
|
5
5
|
class MaxIterations < StandardError
|
6
6
|
attr_reader :iterator
|
@@ -83,6 +83,8 @@ class ModelIterator
|
|
83
83
|
# at a time.
|
84
84
|
# :limit - Fixnum limit of objects to fetch from the db.
|
85
85
|
# Default: 100
|
86
|
+
# :conditions - Array of String SQL WHERE clause and optional values
|
87
|
+
# (Will override clause/values given in arguments.)
|
86
88
|
#
|
87
89
|
# ModelIterator.new(Repository, :start_id => 5000)
|
88
90
|
# ModelIterator.new(Repository, 'public=?', true, :start_id => 1000)
|
@@ -101,10 +103,15 @@ class ModelIterator
|
|
101
103
|
op = @order == :asc ? '>' : '<'
|
102
104
|
@max = @options[:max].to_i
|
103
105
|
@joins = @options[:joins]
|
104
|
-
@clause =
|
105
|
-
|
106
|
-
|
107
|
-
|
106
|
+
@clause = "#{@id_clause} #{op} ?"
|
107
|
+
if @options[:conditions]
|
108
|
+
conditions = Array(@options[:conditions])
|
109
|
+
@clause += " AND (#{conditions.first})"
|
110
|
+
@clause_args = conditions[1..-1]
|
111
|
+
elsif !args.empty?
|
112
|
+
@clause += " AND (#{args.shift})"
|
113
|
+
@clause_args = args
|
114
|
+
end
|
108
115
|
@current_id = @options[:start_id]
|
109
116
|
@limit = @options[:limit] || 100
|
110
117
|
@job = @prefix = @key = nil
|
data/model_iterator.gemspec
CHANGED
@@ -12,8 +12,8 @@ Gem::Specification.new do |s|
|
|
12
12
|
## If your rubyforge_project name is different, then edit it and comment out
|
13
13
|
## the sub! line in the Rakefile
|
14
14
|
s.name = 'model_iterator'
|
15
|
-
s.version = '1.0.
|
16
|
-
s.date = '
|
15
|
+
s.version = '1.0.2'
|
16
|
+
s.date = '2013-03-19'
|
17
17
|
s.rubyforge_project = 'model_iterator'
|
18
18
|
|
19
19
|
## Make sure your summary is short. The description may be as long
|
@@ -46,6 +46,8 @@ Gem::Specification.new do |s|
|
|
46
46
|
Rakefile
|
47
47
|
lib/model_iterator.rb
|
48
48
|
model_iterator.gemspec
|
49
|
+
script/bootstrap
|
50
|
+
script/test
|
49
51
|
test/helper.rb
|
50
52
|
test/init_test.rb
|
51
53
|
test/iterate_test.rb
|
data/script/bootstrap
ADDED
data/script/test
ADDED
data/test/init_test.rb
CHANGED
@@ -87,3 +87,78 @@ class InitializationTestWithCustomWhereClause < ModelIterator::TestCase
|
|
87
87
|
end
|
88
88
|
end
|
89
89
|
|
90
|
+
class InitializationTestWithCustomWhereClauseInOptions < ModelIterator::TestCase
|
91
|
+
def setup
|
92
|
+
@iter = ModelIterator.new Model,
|
93
|
+
:redis => RedisClient.new, :start_id => 5, :limit => 10,
|
94
|
+
:conditions => ['public = ?', true]
|
95
|
+
end
|
96
|
+
|
97
|
+
def test_sets_klass
|
98
|
+
assert_equal Model, @iter.klass
|
99
|
+
end
|
100
|
+
|
101
|
+
def test_sets_current_id
|
102
|
+
assert_equal 5, @iter.current_id
|
103
|
+
end
|
104
|
+
|
105
|
+
def test_sets_conditions
|
106
|
+
assert_equal ['models.id > ? AND (public = ?)', @iter.current_id, true], @iter.conditions
|
107
|
+
end
|
108
|
+
|
109
|
+
def test_sets_limit
|
110
|
+
assert_equal 10, @iter.limit
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
class InitializationTestWithCustomWhereClauseInOptionsOverridingArguments < ModelIterator::TestCase
|
115
|
+
def setup
|
116
|
+
@iter = ModelIterator.new Model,
|
117
|
+
'unknown = ?',
|
118
|
+
false,
|
119
|
+
:redis => RedisClient.new, :start_id => 5, :limit => 10,
|
120
|
+
:conditions => ['public = ?', true]
|
121
|
+
end
|
122
|
+
|
123
|
+
def test_sets_klass
|
124
|
+
assert_equal Model, @iter.klass
|
125
|
+
end
|
126
|
+
|
127
|
+
def test_sets_current_id
|
128
|
+
assert_equal 5, @iter.current_id
|
129
|
+
end
|
130
|
+
|
131
|
+
def test_sets_conditions
|
132
|
+
assert_equal ['models.id > ? AND (public = ?)', @iter.current_id, true], @iter.conditions
|
133
|
+
end
|
134
|
+
|
135
|
+
def test_sets_limit
|
136
|
+
assert_equal 10, @iter.limit
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
class InitializationTestWithCustomWhereClauseInOptionsAsSql < ModelIterator::TestCase
|
141
|
+
def setup
|
142
|
+
@iter = ModelIterator.new Model,
|
143
|
+
:redis => RedisClient.new, :start_id => 5, :limit => 10,
|
144
|
+
:conditions => 'public = true'
|
145
|
+
end
|
146
|
+
|
147
|
+
def test_sets_klass
|
148
|
+
assert_equal Model, @iter.klass
|
149
|
+
end
|
150
|
+
|
151
|
+
def test_sets_current_id
|
152
|
+
assert_equal 5, @iter.current_id
|
153
|
+
end
|
154
|
+
|
155
|
+
def test_sets_conditions
|
156
|
+
assert_equal ['models.id > ? AND (public = true)', @iter.current_id], @iter.conditions
|
157
|
+
end
|
158
|
+
|
159
|
+
def test_sets_limit
|
160
|
+
assert_equal 10, @iter.limit
|
161
|
+
end
|
162
|
+
end
|
163
|
+
|
164
|
+
|
data/test/iterate_test.rb
CHANGED
@@ -27,6 +27,30 @@ class IterateTest < ModelIterator::TestCase
|
|
27
27
|
assert_equal %w(b c), names
|
28
28
|
end
|
29
29
|
|
30
|
+
def test_loops_through_filtered_records_from_options
|
31
|
+
names = []
|
32
|
+
iter = ModelIterator.new Model,
|
33
|
+
:redis => RedisClient.new, :limit => 1,
|
34
|
+
:conditions => ['name != ?', 'a']
|
35
|
+
iter.each do |m|
|
36
|
+
names << m.name
|
37
|
+
end
|
38
|
+
|
39
|
+
assert_equal %w(b c), names
|
40
|
+
end
|
41
|
+
|
42
|
+
def test_loops_through_filtered_records_from_options_as_plain_sql
|
43
|
+
names = []
|
44
|
+
iter = ModelIterator.new Model,
|
45
|
+
:redis => RedisClient.new, :limit => 1,
|
46
|
+
:conditions => "name != 'a'"
|
47
|
+
iter.each do |m|
|
48
|
+
names << m.name
|
49
|
+
end
|
50
|
+
|
51
|
+
assert_equal %w(b c), names
|
52
|
+
end
|
53
|
+
|
30
54
|
def test_loops_through_records_in_reverse
|
31
55
|
names = []
|
32
56
|
iter = ModelIterator.new Model, :redis => RedisClient.new, :limit => 1,
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: model_iterator
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.2
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date:
|
12
|
+
date: 2013-03-19 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: rake
|
@@ -55,6 +55,8 @@ files:
|
|
55
55
|
- Rakefile
|
56
56
|
- lib/model_iterator.rb
|
57
57
|
- model_iterator.gemspec
|
58
|
+
- script/bootstrap
|
59
|
+
- script/test
|
58
60
|
- test/helper.rb
|
59
61
|
- test/init_test.rb
|
60
62
|
- test/iterate_test.rb
|
@@ -72,7 +74,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
72
74
|
version: '0'
|
73
75
|
segments:
|
74
76
|
- 0
|
75
|
-
hash:
|
77
|
+
hash: 1002102300965983738
|
76
78
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
77
79
|
none: false
|
78
80
|
requirements:
|