embulk-filter-insert 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +5 -0
- data/Gemfile +2 -0
- data/LICENSE.txt +21 -0
- data/README.md +101 -0
- data/Rakefile +3 -0
- data/embulk-filter-insert.gemspec +19 -0
- data/lib/embulk/filter/insert.rb +144 -0
- metadata +80 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 09934c336dd5ea3b9af1e9e52a7ba4f5647bac8d
|
4
|
+
data.tar.gz: afa263b7fbe96133f5149cf271443a0efbcbc60a
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 69433687684b90978a8363801d9aded46144f805f7b88ca15bf4f0214408ce452892e9a3269e83e67d3b7b00c1bc22a37f3a0068ceb53b8d385a6fa2731b1d17
|
7
|
+
data.tar.gz: 4af757d250752ac14cf85cbcf563ccb245d308a5b57ab82f3b3f2495509e8e9d4d9df4d3abc58dce06d79392b196398a01cd9813d4df0e51cdfa3482eab239f6
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
|
2
|
+
MIT License
|
3
|
+
|
4
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
5
|
+
a copy of this software and associated documentation files (the
|
6
|
+
"Software"), to deal in the Software without restriction, including
|
7
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be
|
13
|
+
included in all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
16
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
18
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
19
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
20
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
21
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,101 @@
|
|
1
|
+
# Insert filter plugin for Embulk
|
2
|
+
|
3
|
+
Embulk filter plugin that inserts column(s) at any position (e.g., the top/bottom of the columns, before/after the specified column name)
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: filter
|
8
|
+
|
9
|
+
## Configuration
|
10
|
+
|
11
|
+
### Column(s)
|
12
|
+
|
13
|
+
Either "column" or "columns" is required for specifying inserted column(s).
|
14
|
+
|
15
|
+
- **column**: associative array that contains only one key-value pair (key means a column name, value means a constant value in the column)
|
16
|
+
- **columns**: List of the associative arrays
|
17
|
+
|
18
|
+
The "column" associate array can contain following optional configuration.
|
19
|
+
|
20
|
+
- **as**: type of the constant vaule in the column, i.e. boolean, long, double, string or timestamp (string, default: string)
|
21
|
+
|
22
|
+
### Position
|
23
|
+
|
24
|
+
Any of the following configurations is required for specifying a position where new columns are inserted.
|
25
|
+
|
26
|
+
- **at**: "top", "head", "bottom", "tail" or index number where the new column(s) is/are inserted (string)
|
27
|
+
- **before**: column name that comes before the new column(s) (string)
|
28
|
+
- **after**: column name that comes after the new column(s) (string)
|
29
|
+
|
30
|
+
If none of the configurations is specified, the new columns are inserted at the bottom of the existing columns.
|
31
|
+
|
32
|
+
## Example
|
33
|
+
|
34
|
+
Example 1: Insert "host_name" column at the top of the columns
|
35
|
+
|
36
|
+
```yaml
|
37
|
+
filters:
|
38
|
+
- { type: insert, column: { host_name: host01 }, at: top }
|
39
|
+
```
|
40
|
+
|
41
|
+
Example 2: Insert "host_name" column at the bottom of the columns
|
42
|
+
|
43
|
+
```yaml
|
44
|
+
filters:
|
45
|
+
- { type: insert, column: { host_name: host01 }, at: bottom }
|
46
|
+
```
|
47
|
+
|
48
|
+
Example 3: Insert "host_name" column after second column
|
49
|
+
|
50
|
+
```yaml
|
51
|
+
filters:
|
52
|
+
- { type: insert, column: { host_name: host01 }, at: 2 }
|
53
|
+
```
|
54
|
+
|
55
|
+
Example 4: Insert "service_name" column before "host_name" column
|
56
|
+
|
57
|
+
```yaml
|
58
|
+
filters:
|
59
|
+
- { type: insert, column: { service_name: service01 }, before: host_name }
|
60
|
+
```
|
61
|
+
|
62
|
+
Example 5: Insert "service_name" column after "host_name" column
|
63
|
+
|
64
|
+
```yaml
|
65
|
+
filters:
|
66
|
+
- { type: insert, column: { service_name: service01 }, after: host_name }
|
67
|
+
```
|
68
|
+
|
69
|
+
Example 6: Insert "user_id" column as integer at the bottom of the columns
|
70
|
+
|
71
|
+
```yaml
|
72
|
+
filters:
|
73
|
+
- { type: insert, column: { user_id: 1234567, as: long } }
|
74
|
+
```
|
75
|
+
|
76
|
+
Example 7: Insert multiple columns in a row at the bottom of the columns
|
77
|
+
|
78
|
+
```yaml
|
79
|
+
filters:
|
80
|
+
- type: insert
|
81
|
+
columns:
|
82
|
+
- host_name: host01
|
83
|
+
- service_name: service01
|
84
|
+
```
|
85
|
+
|
86
|
+
Example 8: Combination of the above examples
|
87
|
+
|
88
|
+
```yaml
|
89
|
+
filters:
|
90
|
+
- type: insert
|
91
|
+
columns:
|
92
|
+
- service_name: service01
|
93
|
+
- { user_id: 1234567, as: long }
|
94
|
+
after: host_name
|
95
|
+
```
|
96
|
+
|
97
|
+
## Build
|
98
|
+
|
99
|
+
```
|
100
|
+
$ rake
|
101
|
+
```
|
data/Rakefile
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
|
2
|
+
Gem::Specification.new do |spec|
|
3
|
+
spec.name = "embulk-filter-insert"
|
4
|
+
spec.version = "1.0.0"
|
5
|
+
spec.authors = ["muziyoshiz"]
|
6
|
+
spec.summary = "Embulk filter plugin that inserts column(s) at any position"
|
7
|
+
spec.description = "Embulk filter plugin that inserts column(s) at any position (e.g., the top/bottom of the columns, before/after the specified column name)"
|
8
|
+
spec.email = ["muziyoshiz@gmail.com"]
|
9
|
+
spec.licenses = ["MIT"]
|
10
|
+
spec.homepage = "https://github.com/muziyoshiz/embulk-filter-insert"
|
11
|
+
|
12
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
13
|
+
spec.test_files = spec.files.grep(%r{^(test|spec)/})
|
14
|
+
spec.require_paths = ["lib"]
|
15
|
+
|
16
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
17
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
18
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
19
|
+
end
|
@@ -0,0 +1,144 @@
|
|
1
|
+
module Embulk
|
2
|
+
module Filter
|
3
|
+
|
4
|
+
class InsertFilterPlugin < FilterPlugin
|
5
|
+
Plugin.register_filter("insert", self)
|
6
|
+
|
7
|
+
def self.transaction(config, in_schema, &control)
|
8
|
+
task = {}
|
9
|
+
|
10
|
+
column = config.param("column", :hash, default: nil)
|
11
|
+
columns = config.param("columns", :array, default: nil)
|
12
|
+
# ^ = XOR
|
13
|
+
unless (column.nil? ^ columns.nil?)
|
14
|
+
raise ArgumentError, "Either \"column\" or \"columns\" is needed"
|
15
|
+
end
|
16
|
+
|
17
|
+
if column
|
18
|
+
columns = [ InsertFilterPlugin.get_column(column) ]
|
19
|
+
else
|
20
|
+
columns = InsertFilterPlugin.get_columns(columns)
|
21
|
+
end
|
22
|
+
|
23
|
+
task["values"] = columns.map{|c| c[:value] }
|
24
|
+
|
25
|
+
at = config.param("at", :string, default: nil)
|
26
|
+
before = config.param("before", :string, default: nil)
|
27
|
+
after = config.param("after", :string, default: nil)
|
28
|
+
|
29
|
+
if at.nil? and before.nil? and after.nil?
|
30
|
+
at = "bottom"
|
31
|
+
end
|
32
|
+
|
33
|
+
no_of_position_param = 0
|
34
|
+
no_of_position_param += 1 unless at.nil?
|
35
|
+
no_of_position_param += 1 unless before.nil?
|
36
|
+
no_of_position_param += 1 unless after.nil?
|
37
|
+
|
38
|
+
unless no_of_position_param == 1
|
39
|
+
raise ArgumentError, "Either \"at\", \"before\" or \"after\" is needed"
|
40
|
+
end
|
41
|
+
|
42
|
+
if at
|
43
|
+
case at
|
44
|
+
when "top", "head"
|
45
|
+
task["position"] = 0
|
46
|
+
when "bottom", "tail"
|
47
|
+
task["position"] = in_schema.size
|
48
|
+
else
|
49
|
+
task["position"] = at.to_i
|
50
|
+
end
|
51
|
+
elsif before
|
52
|
+
schema_cols = in_schema.select{|c| c.name == before }
|
53
|
+
if schema_cols.empty?
|
54
|
+
raise ArgumentError, "Column #{before} is not found"
|
55
|
+
end
|
56
|
+
task["position"] = schema_cols[0].index
|
57
|
+
else
|
58
|
+
schema_cols = in_schema.select{|c| c.name == after }
|
59
|
+
if schema_cols.empty?
|
60
|
+
raise ArgumentError, "Column #{after} is not found"
|
61
|
+
end
|
62
|
+
task["position"] = schema_cols[0].index + 1
|
63
|
+
end
|
64
|
+
|
65
|
+
# modify column definition
|
66
|
+
inserted_schema = []
|
67
|
+
columns.each{|c| inserted_schema.push(Column.new(0, c[:name], c[:type])) }
|
68
|
+
out_columns = in_schema.map{|c| c }
|
69
|
+
out_columns.insert(task["position"], *inserted_schema)
|
70
|
+
|
71
|
+
# renumber index
|
72
|
+
out_columns.each_with_index{|c, idx| c.index = idx }
|
73
|
+
|
74
|
+
yield(task, out_columns)
|
75
|
+
end
|
76
|
+
|
77
|
+
# return { :name => name1, :value => value1, :type => type1 }
|
78
|
+
def self.get_column(column_hash)
|
79
|
+
if column_hash.size > 2
|
80
|
+
raise ArgumentError, "Invalid column parameter: #{column_hash.to_s}"
|
81
|
+
end
|
82
|
+
|
83
|
+
# default type is string
|
84
|
+
type = :string
|
85
|
+
|
86
|
+
if column_hash.size == 2
|
87
|
+
unless column_hash.keys.include?("as")
|
88
|
+
raise ArgumentError, "Invalid column parameter: #{column_hash.to_s}"
|
89
|
+
end
|
90
|
+
type = column_hash["as"].to_sym
|
91
|
+
column_hash = column_hash.select{|k, v| k != "as" }
|
92
|
+
end
|
93
|
+
|
94
|
+
column = {
|
95
|
+
:name => column_hash.keys.first,
|
96
|
+
:value => column_hash.values.first,
|
97
|
+
:type => type
|
98
|
+
}
|
99
|
+
|
100
|
+
case type
|
101
|
+
when :boolean
|
102
|
+
column[:value] = (column[:value] != "false")
|
103
|
+
when :long
|
104
|
+
column[:value] = column[:value].to_i
|
105
|
+
when :double
|
106
|
+
column[:value] = column[:value].to_f
|
107
|
+
when :string
|
108
|
+
# do nothing
|
109
|
+
when :timestamp
|
110
|
+
column[:value] = Date.parse(column[:value])
|
111
|
+
else
|
112
|
+
raise ArgumentError, "Unknown type #{type}: supported types are boolean, long, double, string and timestamp"
|
113
|
+
end
|
114
|
+
|
115
|
+
column
|
116
|
+
end
|
117
|
+
|
118
|
+
# return array of column
|
119
|
+
def self.get_columns(columns_array)
|
120
|
+
columns_array.map{|column_hash| InsertFilterPlugin.get_column(column_hash) }
|
121
|
+
end
|
122
|
+
|
123
|
+
def init
|
124
|
+
@values = task["values"]
|
125
|
+
@position = task["position"]
|
126
|
+
end
|
127
|
+
|
128
|
+
def close
|
129
|
+
end
|
130
|
+
|
131
|
+
def add(page)
|
132
|
+
page.each do |record|
|
133
|
+
record.insert(@position, *@values)
|
134
|
+
page_builder.add(record)
|
135
|
+
end
|
136
|
+
end
|
137
|
+
|
138
|
+
def finish
|
139
|
+
page_builder.finish
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
end
|
144
|
+
end
|
metadata
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-filter-insert
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- muziyoshiz
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-06-25 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
description: Embulk filter plugin that inserts column(s) at any position (e.g., the
|
42
|
+
top/bottom of the columns, before/after the specified column name)
|
43
|
+
email:
|
44
|
+
- muziyoshiz@gmail.com
|
45
|
+
executables: []
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- .gitignore
|
50
|
+
- Gemfile
|
51
|
+
- LICENSE.txt
|
52
|
+
- README.md
|
53
|
+
- Rakefile
|
54
|
+
- embulk-filter-insert.gemspec
|
55
|
+
- lib/embulk/filter/insert.rb
|
56
|
+
homepage: https://github.com/muziyoshiz/embulk-filter-insert
|
57
|
+
licenses:
|
58
|
+
- MIT
|
59
|
+
metadata: {}
|
60
|
+
post_install_message:
|
61
|
+
rdoc_options: []
|
62
|
+
require_paths:
|
63
|
+
- lib
|
64
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
70
|
+
requirements:
|
71
|
+
- - '>='
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
version: '0'
|
74
|
+
requirements: []
|
75
|
+
rubyforge_project:
|
76
|
+
rubygems_version: 2.0.14
|
77
|
+
signing_key:
|
78
|
+
specification_version: 4
|
79
|
+
summary: Embulk filter plugin that inserts column(s) at any position
|
80
|
+
test_files: []
|