assimilate 0.2.3 → 0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +1 -1
- data/assimilate.gemspec +1 -0
- data/lib/assimilate/extender.rb +43 -19
- data/lib/assimilate/version.rb +1 -1
- data/spec/data/birthdates.csv +5 -0
- data/spec/lib/extend_spec.rb +48 -0
- metadata +27 -14
data/Rakefile
CHANGED
data/assimilate.gemspec
CHANGED
@@ -20,6 +20,7 @@ Gem::Specification.new do |gem|
|
|
20
20
|
gem.add_dependency "bson_ext", "~> 1.6.0"
|
21
21
|
gem.add_dependency 'activesupport', "~> 3.2.0"
|
22
22
|
|
23
|
+
gem.add_development_dependency "rake", "~> 0.9.2"
|
23
24
|
gem.add_development_dependency "rspec", "~> 2.9.0"
|
24
25
|
gem.add_development_dependency "guard-rspec", "~> 0.7.0"
|
25
26
|
gem.add_development_dependency "ruby_gntp", "~> 0.3.4"
|
data/lib/assimilate/extender.rb
CHANGED
@@ -43,11 +43,14 @@ class Assimilate::Extender
|
|
43
43
|
|
44
44
|
# if there is a field to compare on (i.e. a timestamp), then apply the update if the timestamp is newer;
|
45
45
|
# otherwise (no timestamp) compare the hashes and apply if there are any differences.
|
46
|
-
def apply_this_update(current_record, new_data)
|
47
|
-
if @comparison_field && current_record[
|
48
|
-
is_newer(current_record[
|
46
|
+
def apply_this_update?(current_record, new_data)
|
47
|
+
if @comparison_field && current_record[keyfield]
|
48
|
+
is_newer(current_record[keyfield], new_data)
|
49
|
+
elsif keyfield
|
50
|
+
current_record[keyfield] != new_data
|
49
51
|
else
|
50
|
-
|
52
|
+
# top-level extension - compare all the attributes to be added
|
53
|
+
new_data.select {|k,v| current_record[k] != v}.any?
|
51
54
|
end
|
52
55
|
end
|
53
56
|
|
@@ -60,7 +63,7 @@ class Assimilate::Extender
|
|
60
63
|
# @seen[key] = data
|
61
64
|
current_record = @baseline[key]
|
62
65
|
if current_record
|
63
|
-
if apply_this_update(current_record, data)
|
66
|
+
if apply_this_update?(current_record, data)
|
64
67
|
@changes << key
|
65
68
|
@seen[key] = data
|
66
69
|
else
|
@@ -98,11 +101,21 @@ class Assimilate::Extender
|
|
98
101
|
def apply_inserts
|
99
102
|
@adds.each do |key|
|
100
103
|
data = @seen[key]
|
101
|
-
|
102
|
-
@
|
103
|
-
|
104
|
-
|
105
|
-
|
104
|
+
if keyfield
|
105
|
+
@catalog.catalog.insert(
|
106
|
+
@domainkey => domain,
|
107
|
+
idfield => key,
|
108
|
+
keyfield => data
|
109
|
+
)
|
110
|
+
else
|
111
|
+
# top-level extension
|
112
|
+
@catalog.catalog.insert(
|
113
|
+
data.merge(
|
114
|
+
@domainkey => domain,
|
115
|
+
idfield => key
|
116
|
+
)
|
117
|
+
)
|
118
|
+
end
|
106
119
|
end
|
107
120
|
end
|
108
121
|
|
@@ -110,16 +123,27 @@ class Assimilate::Extender
|
|
110
123
|
def apply_updates
|
111
124
|
@changes.each do |key|
|
112
125
|
data = @seen[key]
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
126
|
+
if keyfield
|
127
|
+
@catalog.catalog.update(
|
128
|
+
{
|
129
|
+
@domainkey => domain,
|
130
|
+
idfield => key
|
131
|
+
},
|
132
|
+
{"$set" => {
|
133
|
+
keyfield => data
|
134
|
+
}
|
120
135
|
}
|
121
|
-
|
122
|
-
|
136
|
+
)
|
137
|
+
else
|
138
|
+
# top-level extension
|
139
|
+
@catalog.catalog.update(
|
140
|
+
{
|
141
|
+
@domainkey => domain,
|
142
|
+
idfield => key
|
143
|
+
},
|
144
|
+
{"$set" => data }
|
145
|
+
)
|
146
|
+
end
|
123
147
|
end
|
124
148
|
end
|
125
149
|
|
data/lib/assimilate/version.rb
CHANGED
data/spec/lib/extend_spec.rb
CHANGED
@@ -30,6 +30,14 @@ describe "loading extended data" do
|
|
30
30
|
@extender.commit
|
31
31
|
end
|
32
32
|
|
33
|
+
def import_toplevel_extended_data(datestamp, filename, opts = {})
|
34
|
+
@extender = @catalog.extend_data(opts.merge(domain: 'testdata', datestamp: datestamp, idfield: 'ID'))
|
35
|
+
Assimilate.slurp(File.dirname(__FILE__) + "/../data/#{filename}") do |rec|
|
36
|
+
@extender << rec
|
37
|
+
end
|
38
|
+
@extender.commit
|
39
|
+
end
|
40
|
+
|
33
41
|
describe "into matching catalog entries" do
|
34
42
|
before(:all) do
|
35
43
|
reset_catalog
|
@@ -70,6 +78,46 @@ describe "loading extended data" do
|
|
70
78
|
end
|
71
79
|
end
|
72
80
|
|
81
|
+
describe "at top level of catalog entries" do
|
82
|
+
before(:all) do
|
83
|
+
reset_catalog
|
84
|
+
import_base_data("123")
|
85
|
+
end
|
86
|
+
|
87
|
+
before(:each) do
|
88
|
+
import_toplevel_extended_data("991", "birthdates.csv")
|
89
|
+
end
|
90
|
+
|
91
|
+
it "should capture changes" do
|
92
|
+
@extender.stats.should == {
|
93
|
+
:baseline_count => 6,
|
94
|
+
:final_count => 7,
|
95
|
+
:distinct_ids => 4,
|
96
|
+
:adds_count => 1,
|
97
|
+
:new_ids => ['999'],
|
98
|
+
:updates_count => 3,
|
99
|
+
:updated_fields => {'birthdate' => 4},
|
100
|
+
:unchanged_count => 0
|
101
|
+
}
|
102
|
+
end
|
103
|
+
|
104
|
+
it "should do no-ops on duplicate load" do
|
105
|
+
# import_extended_data("1002", "dates")
|
106
|
+
lambda {import_toplevel_extended_data("992", "birthdates.csv")}.should_not raise_error
|
107
|
+
|
108
|
+
@extender.stats.should == {
|
109
|
+
:baseline_count => 7,
|
110
|
+
:final_count => 7,
|
111
|
+
:distinct_ids => 4,
|
112
|
+
:adds_count => 0,
|
113
|
+
:new_ids => [],
|
114
|
+
:updates_count => 0,
|
115
|
+
:updated_fields => {},
|
116
|
+
:unchanged_count => 4
|
117
|
+
}
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
73
121
|
describe "updating log entries" do
|
74
122
|
before(:all) do
|
75
123
|
reset_catalog
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: assimilate
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: '0.3'
|
5
5
|
prerelease:
|
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: 2012-
|
12
|
+
date: 2012-06-06 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mongo
|
16
|
-
requirement: &
|
16
|
+
requirement: &2161063380 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ~>
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: 1.6.0
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *2161063380
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: bson_ext
|
27
|
-
requirement: &
|
27
|
+
requirement: &2161062840 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ~>
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: 1.6.0
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *2161062840
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: activesupport
|
38
|
-
requirement: &
|
38
|
+
requirement: &2161062360 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ~>
|
@@ -43,10 +43,21 @@ dependencies:
|
|
43
43
|
version: 3.2.0
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *2161062360
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: rake
|
49
|
+
requirement: &2161061860 !ruby/object:Gem::Requirement
|
50
|
+
none: false
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 0.9.2
|
55
|
+
type: :development
|
56
|
+
prerelease: false
|
57
|
+
version_requirements: *2161061860
|
47
58
|
- !ruby/object:Gem::Dependency
|
48
59
|
name: rspec
|
49
|
-
requirement: &
|
60
|
+
requirement: &2161061380 !ruby/object:Gem::Requirement
|
50
61
|
none: false
|
51
62
|
requirements:
|
52
63
|
- - ~>
|
@@ -54,10 +65,10 @@ dependencies:
|
|
54
65
|
version: 2.9.0
|
55
66
|
type: :development
|
56
67
|
prerelease: false
|
57
|
-
version_requirements: *
|
68
|
+
version_requirements: *2161061380
|
58
69
|
- !ruby/object:Gem::Dependency
|
59
70
|
name: guard-rspec
|
60
|
-
requirement: &
|
71
|
+
requirement: &2161060880 !ruby/object:Gem::Requirement
|
61
72
|
none: false
|
62
73
|
requirements:
|
63
74
|
- - ~>
|
@@ -65,10 +76,10 @@ dependencies:
|
|
65
76
|
version: 0.7.0
|
66
77
|
type: :development
|
67
78
|
prerelease: false
|
68
|
-
version_requirements: *
|
79
|
+
version_requirements: *2161060880
|
69
80
|
- !ruby/object:Gem::Dependency
|
70
81
|
name: ruby_gntp
|
71
|
-
requirement: &
|
82
|
+
requirement: &2161060380 !ruby/object:Gem::Requirement
|
72
83
|
none: false
|
73
84
|
requirements:
|
74
85
|
- - ~>
|
@@ -76,7 +87,7 @@ dependencies:
|
|
76
87
|
version: 0.3.4
|
77
88
|
type: :development
|
78
89
|
prerelease: false
|
79
|
-
version_requirements: *
|
90
|
+
version_requirements: *2161060380
|
80
91
|
description: Ingest updates from CSV and apply to set of hashes
|
81
92
|
email:
|
82
93
|
- jmay@pobox.com
|
@@ -100,6 +111,7 @@ files:
|
|
100
111
|
- lib/assimilate/extender.rb
|
101
112
|
- lib/assimilate/version.rb
|
102
113
|
- spec/data/batch_input.csv
|
114
|
+
- spec/data/birthdates.csv
|
103
115
|
- spec/data/dates.csv
|
104
116
|
- spec/data/duplicate_input.csv
|
105
117
|
- spec/data/logs1.csv
|
@@ -135,6 +147,7 @@ specification_version: 3
|
|
135
147
|
summary: Review & incorporate changes to a repository of persistent hashes in mongodb.
|
136
148
|
test_files:
|
137
149
|
- spec/data/batch_input.csv
|
150
|
+
- spec/data/birthdates.csv
|
138
151
|
- spec/data/dates.csv
|
139
152
|
- spec/data/duplicate_input.csv
|
140
153
|
- spec/data/logs1.csv
|