assimilate 0.0.4 → 0.0.5
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/assimilate/batch.rb +14 -10
- data/lib/assimilate/catalog.rb +2 -1
- data/lib/assimilate/version.rb +1 -1
- data/lib/assimilate.rb +1 -1
- data/spec/data/batch_input.csv +7 -7
- data/spec/data/duplicate_input.csv +7 -7
- data/spec/data/updates.csv +6 -6
- data/spec/lib/batch_spec.rb +10 -6
- metadata +14 -14
data/lib/assimilate/batch.rb
CHANGED
@@ -13,7 +13,7 @@ class Assimilate::Batch
|
|
13
13
|
load_baseline
|
14
14
|
|
15
15
|
@noops = []
|
16
|
-
@changes =
|
16
|
+
@changes = {}
|
17
17
|
@adds = []
|
18
18
|
@deletes = []
|
19
19
|
@resolved = false
|
@@ -45,22 +45,26 @@ class Assimilate::Batch
|
|
45
45
|
if current_record == hash
|
46
46
|
@noops << hash
|
47
47
|
else
|
48
|
-
@changes
|
48
|
+
@changes[key] = deltas(current_record, hash)
|
49
49
|
end
|
50
50
|
else
|
51
51
|
@adds << hash
|
52
52
|
end
|
53
53
|
end
|
54
54
|
|
55
|
+
def deltas(h1,h2)
|
56
|
+
(h1.keys | h2.keys).each_with_object({}) {|k,h| h[k] = h2[k] if h1[k] != h2[k]}
|
57
|
+
end
|
58
|
+
|
55
59
|
# compute anything needed before we can write updates to permanent store
|
56
60
|
# * find records that have been deleted
|
57
61
|
def resolve
|
58
62
|
if !@resolved
|
59
63
|
@deleted_keys = (@baseline.keys - @seen.keys).reject {|k| @baseline[k][@catalog.config[:deletion_marker]]}
|
60
64
|
|
61
|
-
@updated_field_counts = @changes.each_with_object(Hash.new(0)) do |
|
62
|
-
key = rec[idfield]
|
63
|
-
diffs =
|
65
|
+
@updated_field_counts = @changes.each_with_object(Hash.new(0)) do |(key,diffs),h|
|
66
|
+
# key = rec[idfield]
|
67
|
+
# diffs = deltas(stripped_record_for(key), rec)
|
64
68
|
diffs.keys.each do |f|
|
65
69
|
h[f] += 1
|
66
70
|
end
|
@@ -79,8 +83,8 @@ class Assimilate::Batch
|
|
79
83
|
:new_ids => @adds.map {|rec| rec[idfield]},
|
80
84
|
:deletes_count => @deleted_keys.count,
|
81
85
|
:deleted_ids => @deleted_keys,
|
82
|
-
:updates_count => @changes.
|
83
|
-
:updated_ids => @changes.
|
86
|
+
:updates_count => @changes.size,
|
87
|
+
:updated_ids => @changes.keys,
|
84
88
|
:unchanged_count => @noops.count,
|
85
89
|
:updated_fields => @updated_field_counts
|
86
90
|
}
|
@@ -128,13 +132,13 @@ class Assimilate::Batch
|
|
128
132
|
end
|
129
133
|
|
130
134
|
def apply_updates
|
131
|
-
@changes.each do |
|
135
|
+
@changes.each do |key, diffs|
|
132
136
|
@catalog.catalog.update(
|
133
137
|
{
|
134
138
|
@domainkey => domain,
|
135
|
-
idfield =>
|
139
|
+
idfield => key
|
136
140
|
},
|
137
|
-
{"$set" =>
|
141
|
+
{"$set" => diffs}
|
138
142
|
)
|
139
143
|
end
|
140
144
|
end
|
data/lib/assimilate/catalog.rb
CHANGED
data/lib/assimilate/version.rb
CHANGED
data/lib/assimilate.rb
CHANGED
data/spec/data/batch_input.csv
CHANGED
@@ -1,7 +1,7 @@
|
|
1
|
-
ID,name,title
|
2
|
-
1,George Washington,President
|
3
|
-
2,John Adams,Vice President
|
4
|
-
3,Benjamin Franklin,Sage
|
5
|
-
4,Aaron Burr,Duelist
|
6
|
-
5,Alexander Hamilton,Financier
|
7
|
-
6,James Madison,Theorist
|
1
|
+
ID,name,title,spouse
|
2
|
+
1,George Washington,President,Martha
|
3
|
+
2,John Adams,Vice President,Abigail
|
4
|
+
3,Benjamin Franklin,Sage,Deborah
|
5
|
+
4,Aaron Burr,Duelist,Theodosia
|
6
|
+
5,Alexander Hamilton,Financier,Elizabeth
|
7
|
+
6,James Madison,Theorist,Dolly
|
@@ -1,7 +1,7 @@
|
|
1
|
-
ID,name,title
|
2
|
-
1,George Washington,President
|
3
|
-
2,John Adams,Vice President
|
4
|
-
3,Benjamin Franklin,Sage
|
5
|
-
4,Aaron Burr,Duelist
|
6
|
-
5,Alexander Hamilton,Financier
|
7
|
-
6,James Madison,Theorist
|
1
|
+
ID,name,title,spouse
|
2
|
+
1,George Washington,President,Martha
|
3
|
+
2,John Adams,Vice President,Abigail
|
4
|
+
3,Benjamin Franklin,Sage,Deborah
|
5
|
+
4,Aaron Burr,Duelist,Theodosia
|
6
|
+
5,Alexander Hamilton,Financier,Elizabeth
|
7
|
+
6,James Madison,Theorist,Dolly
|
data/spec/data/updates.csv
CHANGED
@@ -1,6 +1,6 @@
|
|
1
|
-
ID,name,title
|
2
|
-
1,George Washington,President
|
3
|
-
2,John Adams,Vice President
|
4
|
-
3,Benjamin Franklin,Ambassador
|
5
|
-
5,Alexander Hamilton,Financier
|
6
|
-
7,Thomas Jefferson,Anti-Federalist
|
1
|
+
ID,name,title,spouse
|
2
|
+
1,George Washington,President,Martha
|
3
|
+
2,John Adams,Vice President,Abigail
|
4
|
+
3,Benjamin Franklin,Ambassador,
|
5
|
+
5,Alexander Hamilton,Financier,Elizabeth
|
6
|
+
7,Thomas Jefferson,Anti-Federalist,
|
data/spec/lib/batch_spec.rb
CHANGED
@@ -45,15 +45,16 @@ describe "importing file" do
|
|
45
45
|
|
46
46
|
it "should load the records verbatim" do
|
47
47
|
@catalog.catalog.count.should == 6
|
48
|
-
@catalog.where('_resource' => 'testdata', 'ID' => '3').should ==
|
48
|
+
@catalog.where('_resource' => 'testdata', 'ID' => '3').should ==
|
49
|
+
{'ID' => '3', 'name' => 'Benjamin Franklin', 'title' => 'Sage', 'spouse' => 'Deborah'}
|
49
50
|
end
|
50
51
|
|
51
52
|
it "should refuse to do a duplicate import" do
|
52
|
-
lambda {import_data("123")}.should raise_error(Assimilate::DuplicateImportError)
|
53
|
+
lambda {import_data("123")}.should raise_error(Assimilate::DuplicateImportError, "duplicate batch for datestamp 123")
|
53
54
|
end
|
54
55
|
|
55
56
|
it "should refuse to re-import same file" do
|
56
|
-
lambda {import_data("234")}.should raise_error(Assimilate::DuplicateImportError)
|
57
|
+
lambda {import_data("234")}.should raise_error(Assimilate::DuplicateImportError, "duplicate batch for file batch_input.csv")
|
57
58
|
end
|
58
59
|
|
59
60
|
it "should do all no-ops when importing identical data" do
|
@@ -78,9 +79,7 @@ describe "importing file" do
|
|
78
79
|
before(:all) do
|
79
80
|
reset_catalog
|
80
81
|
import_data("123")
|
81
|
-
end
|
82
82
|
|
83
|
-
before(:each) do
|
84
83
|
import_data("345", "updates.csv")
|
85
84
|
end
|
86
85
|
|
@@ -95,9 +94,14 @@ describe "importing file" do
|
|
95
94
|
:updates_count => 1,
|
96
95
|
:updated_ids => ['3'],
|
97
96
|
:unchanged_count => 3,
|
98
|
-
:updated_fields => {'title' => 1}
|
97
|
+
:updated_fields => {'title' => 1, 'spouse' => 1}
|
99
98
|
}
|
100
99
|
@catalog.active_count.should == 5
|
101
100
|
end
|
101
|
+
|
102
|
+
it "should handle deleted attributes" do
|
103
|
+
franklin = @catalog.where('ID' => '3')
|
104
|
+
franklin['spouse'].should be_nil
|
105
|
+
end
|
102
106
|
end
|
103
107
|
end
|
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: 0.0.
|
4
|
+
version: 0.0.5
|
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: 2012-05-
|
12
|
+
date: 2012-05-03 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mongo
|
16
|
-
requirement: &
|
16
|
+
requirement: &2157608660 !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: *2157608660
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: bson_ext
|
27
|
-
requirement: &
|
27
|
+
requirement: &2157607760 !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: *2157607760
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: activesupport
|
38
|
-
requirement: &
|
38
|
+
requirement: &2157607080 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ~>
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: 3.2.0
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *2157607080
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: rspec
|
49
|
-
requirement: &
|
49
|
+
requirement: &2157606260 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ~>
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: 2.9.0
|
55
55
|
type: :development
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *2157606260
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: guard-rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &2157605600 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: 0.7.0
|
66
66
|
type: :development
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *2157605600
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: ruby_gntp
|
71
|
-
requirement: &
|
71
|
+
requirement: &2157603980 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ~>
|
@@ -76,7 +76,7 @@ dependencies:
|
|
76
76
|
version: 0.3.4
|
77
77
|
type: :development
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *2157603980
|
80
80
|
description: Ingest updates from CSV and apply to set of hashes
|
81
81
|
email:
|
82
82
|
- jmay@pobox.com
|