itiel 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.autotest +17 -0
- data/.gitignore +13 -0
- data/.gitlab-ci.yml +36 -0
- data/.rspec +2 -0
- data/.ruby-version +1 -0
- data/.travis.yml +9 -0
- data/Gemfile +4 -0
- data/Gemfile.rails.4.0 +7 -0
- data/Gemfile.rails.4.1 +7 -0
- data/Gemfile.rails.4.2 +7 -0
- data/README.markdown +106 -0
- data/Rakefile +13 -0
- data/build.sh +10 -0
- data/features/extract/database_table.feature +16 -0
- data/features/extract/sql_script.feature +17 -0
- data/features/load/database_table_loader.feature +21 -0
- data/features/lookup/csv_file.feature +41 -0
- data/features/lookup/database_table.feature +43 -0
- data/features/script/ruby_script.feature +19 -0
- data/features/step_definitions/csv_steps.rb +15 -0
- data/features/step_definitions/extractor/csv_file_steps.rb +3 -0
- data/features/step_definitions/extractor/custom_sql_steps.rb +6 -0
- data/features/step_definitions/extractor/database_steps.rb +27 -0
- data/features/step_definitions/extractor/database_table_steps.rb +8 -0
- data/features/step_definitions/extractor/extraction_steps.rb +3 -0
- data/features/step_definitions/flow_steps.rb +9 -0
- data/features/step_definitions/loader/csv_file_steps.rb +4 -0
- data/features/step_definitions/loader/database_table_steps.rb +14 -0
- data/features/step_definitions/lookup/lookup_steps.rb +35 -0
- data/features/step_definitions/scripting/ruby_script_steps.rb +5 -0
- data/features/step_definitions/stream_steps.rb +8 -0
- data/features/step_definitions/transformation/calculated_column_steps.rb +5 -0
- data/features/step_definitions/transformation/calculated_columns_steps.rb +7 -0
- data/features/step_definitions/transformation/constant_column_steps.rb +3 -0
- data/features/step_definitions/transformation/map_values_step.rb +4 -0
- data/features/step_definitions/transformation/rename_column_steps.rb +3 -0
- data/features/step_definitions/transformation/select_column_steps.rb +3 -0
- data/features/step_definitions/transformation/single_column_sort_steps.rb +3 -0
- data/features/support/database.yml +1 -0
- data/features/support/env.rb +13 -0
- data/features/transform/transformations.feature +123 -0
- data/itiel.gemspec +34 -0
- data/lib/itiel.rb +45 -0
- data/lib/itiel/db/connection.rb +24 -0
- data/lib/itiel/db/sql_connectable.rb +33 -0
- data/lib/itiel/db/truncator.rb +30 -0
- data/lib/itiel/extract/chained_step.rb +22 -0
- data/lib/itiel/extract/csv_file.rb +31 -0
- data/lib/itiel/extract/custom_sql.rb +38 -0
- data/lib/itiel/extract/database_table.rb +23 -0
- data/lib/itiel/job.rb +116 -0
- data/lib/itiel/load/chained_step.rb +37 -0
- data/lib/itiel/load/csv_file.rb +45 -0
- data/lib/itiel/load/database_table.rb +34 -0
- data/lib/itiel/load/input_output_behavior.rb +36 -0
- data/lib/itiel/logger.rb +47 -0
- data/lib/itiel/lookup/chained_step.rb +35 -0
- data/lib/itiel/lookup/csv_file.rb +16 -0
- data/lib/itiel/lookup/database_table.rb +36 -0
- data/lib/itiel/lookup/hash_lookup.rb +35 -0
- data/lib/itiel/nameable.rb +6 -0
- data/lib/itiel/script/chained_step.rb +18 -0
- data/lib/itiel/script/ruby_script.rb +31 -0
- data/lib/itiel/script/sql_script.rb +29 -0
- data/lib/itiel/transform/calculated_columns.rb +47 -0
- data/lib/itiel/transform/chained_step.rb +27 -0
- data/lib/itiel/transform/constant_column.rb +35 -0
- data/lib/itiel/transform/input_output_behavior.rb +44 -0
- data/lib/itiel/transform/map_values.rb +43 -0
- data/lib/itiel/transform/remove_column.rb +33 -0
- data/lib/itiel/transform/rename_column.rb +43 -0
- data/lib/itiel/transform/select_column.rb +37 -0
- data/lib/itiel/version.rb +3 -0
- data/spec/db/sql_connectable_spec.rb +20 -0
- data/spec/extract/chained_step_spec.rb +31 -0
- data/spec/extract/csv_file_spec.rb +22 -0
- data/spec/extract/custom_sql_spec.rb +19 -0
- data/spec/extract/database_table_spec.rb +22 -0
- data/spec/job_spec.rb +80 -0
- data/spec/loader/chained_step_spec.rb +39 -0
- data/spec/loader/csv_file_spec.rb +69 -0
- data/spec/loader/database_table_spec.rb +29 -0
- data/spec/lookup/hash_lookup_spec.rb +108 -0
- data/spec/nameable_spec.rb +17 -0
- data/spec/script/chained_step_spec.rb +24 -0
- data/spec/script/ruby_script_spec.rb +18 -0
- data/spec/script/sql_script_spec.rb +41 -0
- data/spec/spec_helper.rb +24 -0
- data/spec/support/config/database.yml +1 -0
- data/spec/support/config/sources.yml +9 -0
- data/spec/transform/calculated_columns_spec.rb +36 -0
- data/spec/transform/chained_step_spec.rb +36 -0
- data/spec/transform/constant_column_spec.rb +22 -0
- data/spec/transform/map_values_spec.rb +26 -0
- data/spec/transform/rename_column_spec.rb +25 -0
- data/spec/transform/select_column_spec.rb +21 -0
- metadata +344 -0
@@ -0,0 +1,30 @@
|
|
1
|
+
module Itiel
|
2
|
+
module DB
|
3
|
+
#
|
4
|
+
# Truncates specified tables
|
5
|
+
#
|
6
|
+
# Usage:
|
7
|
+
#
|
8
|
+
# @truncator = Itiel::DB::Truncator.new "tables", "to", "truncate"
|
9
|
+
# @truncator.connection = :database
|
10
|
+
# @truncator.truncate!
|
11
|
+
#
|
12
|
+
class Truncator
|
13
|
+
include Itiel::Nameable
|
14
|
+
include Itiel::DB::SQLConnectable
|
15
|
+
|
16
|
+
attr_accessor :tables
|
17
|
+
|
18
|
+
def initialize(*tables)
|
19
|
+
self.tables = tables
|
20
|
+
end
|
21
|
+
|
22
|
+
def truncate!
|
23
|
+
tables.each do |table|
|
24
|
+
db = self.class.sequel_connection(connection)
|
25
|
+
db[table.to_sym].truncate
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module Itiel
|
2
|
+
module Extract
|
3
|
+
#
|
4
|
+
# Defines how the initial extractors behave
|
5
|
+
#
|
6
|
+
# All classes including this module must define the in_batches method
|
7
|
+
#
|
8
|
+
module ChainedStep
|
9
|
+
attr_accessor :next_step
|
10
|
+
|
11
|
+
alias :>> :next_step=
|
12
|
+
|
13
|
+
def start
|
14
|
+
self.next_step.input = extract
|
15
|
+
end
|
16
|
+
|
17
|
+
def extract
|
18
|
+
raise Itiel::MethodNotImplementedException.new "extract is not implemented"
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
require 'csv'
|
2
|
+
|
3
|
+
module Itiel
|
4
|
+
module Extract
|
5
|
+
#
|
6
|
+
# Extracts all specified CSV file rows and sends it in batches to
|
7
|
+
# its next step
|
8
|
+
#
|
9
|
+
# Usage:
|
10
|
+
#
|
11
|
+
# csv_file = Itiel::Extract::CSVFile.new('FileName.csv')
|
12
|
+
# csv_file.batch_size = 15
|
13
|
+
# csv.file.start
|
14
|
+
#
|
15
|
+
class CSVFile
|
16
|
+
include ChainedStep
|
17
|
+
include Itiel::Nameable
|
18
|
+
|
19
|
+
attr_accessor :file_name
|
20
|
+
|
21
|
+
def initialize(file_name)
|
22
|
+
self.file_name = file_name
|
23
|
+
end
|
24
|
+
|
25
|
+
def extract
|
26
|
+
lines = CSV.read(self.file_name, :headers => true)
|
27
|
+
lines.collect(&:to_hash)
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'sequel'
|
2
|
+
|
3
|
+
module Itiel
|
4
|
+
module Extract
|
5
|
+
#
|
6
|
+
# Creates a stream from the specified SQL query.
|
7
|
+
# Connection must be defined on a file that's on
|
8
|
+
# config/database.yml by default.
|
9
|
+
#
|
10
|
+
# Usage:
|
11
|
+
#
|
12
|
+
# @custom_sql = Itiel::Extract::CustomSQL.new
|
13
|
+
# @custom_sql.connection = :test
|
14
|
+
# @custom_sql.script = 'SELECT * FROM some_table'
|
15
|
+
#
|
16
|
+
#
|
17
|
+
# You can set a different path for the config file at class level
|
18
|
+
#
|
19
|
+
# Itiel::Extract::CustomSQL.connection_file_path = 'path_to_my_config/database.yml'
|
20
|
+
#
|
21
|
+
class CustomSQL
|
22
|
+
include ChainedStep
|
23
|
+
include Itiel::DB::SQLConnectable
|
24
|
+
include Itiel::Nameable
|
25
|
+
|
26
|
+
attr_accessor :script
|
27
|
+
|
28
|
+
def initialize(*args)
|
29
|
+
self.script = args[0]
|
30
|
+
end
|
31
|
+
|
32
|
+
def extract
|
33
|
+
db = self.class.sequel_connection(connection)
|
34
|
+
db[script].all
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module Itiel
|
2
|
+
module Extract
|
3
|
+
#
|
4
|
+
# Extracts all the contents from a Database table into the stream
|
5
|
+
# and passes it on to it's next_step
|
6
|
+
#
|
7
|
+
# Usage:
|
8
|
+
#
|
9
|
+
# @extractor = Itiel::Extract::DatabaseTable.new
|
10
|
+
# @extractor.connection = :test
|
11
|
+
# @extractor.table_name = 'test_table'
|
12
|
+
#
|
13
|
+
#
|
14
|
+
class DatabaseTable < CustomSQL
|
15
|
+
attr_accessor :table_name
|
16
|
+
|
17
|
+
def extract
|
18
|
+
db = self.class.sequel_connection(connection)
|
19
|
+
db[table_name.to_sym].all
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/lib/itiel/job.rb
ADDED
@@ -0,0 +1,116 @@
|
|
1
|
+
module Itiel
|
2
|
+
class Job
|
3
|
+
attr_accessor :block
|
4
|
+
#
|
5
|
+
# Pass a block to this method to process the ETL steps in order
|
6
|
+
#
|
7
|
+
#
|
8
|
+
# Understands a single line per step:
|
9
|
+
#
|
10
|
+
# Itiel::Job.run do |job|
|
11
|
+
# job.step @source
|
12
|
+
# job.step @destination
|
13
|
+
#
|
14
|
+
# ...
|
15
|
+
# end
|
16
|
+
#
|
17
|
+
#
|
18
|
+
# In this case the @source.output is sent to the @destination's input
|
19
|
+
# A third step on the list would send the @destination's output to its
|
20
|
+
# input
|
21
|
+
#
|
22
|
+
#
|
23
|
+
# Another way to do this is by passing hashes to the step method:
|
24
|
+
#
|
25
|
+
# Itiel::Job.run do |job|
|
26
|
+
# job.step @source => @destination
|
27
|
+
# end
|
28
|
+
#
|
29
|
+
#
|
30
|
+
# You want to use this sintax when creating more complex flows. For example,
|
31
|
+
# you could send a step output to several inputs
|
32
|
+
#
|
33
|
+
# Itiel::Job.run do |job|
|
34
|
+
# job.step @source => [ @destination, @second_destination ]
|
35
|
+
# end
|
36
|
+
#
|
37
|
+
def self.run(&block)
|
38
|
+
Itiel::Logger.log_start_job(self)
|
39
|
+
yield self.new
|
40
|
+
Itiel::Logger.log_end_job(self)
|
41
|
+
end
|
42
|
+
|
43
|
+
#
|
44
|
+
# Use it to define the job steps and then run the job at a later date.
|
45
|
+
#
|
46
|
+
# It returns an instance of a job, you can call run! on that instance later
|
47
|
+
# to actually run the steps defined on the block of the job
|
48
|
+
#
|
49
|
+
# Uses the same syntax as run:
|
50
|
+
#
|
51
|
+
# job = Itiel::Job.define do |job|
|
52
|
+
# job.step @source => @destination
|
53
|
+
# end
|
54
|
+
#
|
55
|
+
# job.run!
|
56
|
+
#
|
57
|
+
# Or
|
58
|
+
#
|
59
|
+
# job = Itiel::Job.define do |job|
|
60
|
+
# job.step @source
|
61
|
+
# job.step @destination
|
62
|
+
#
|
63
|
+
# ...
|
64
|
+
# end
|
65
|
+
#
|
66
|
+
# job.run!
|
67
|
+
#
|
68
|
+
def self.define(&block)
|
69
|
+
self.new(&block)
|
70
|
+
end
|
71
|
+
|
72
|
+
#
|
73
|
+
# Use it to run the steps on a previously defined Job
|
74
|
+
#
|
75
|
+
def run!
|
76
|
+
Itiel::Logger.log_start_job(self)
|
77
|
+
self.block.call(self)
|
78
|
+
Itiel::Logger.log_end_job(self)
|
79
|
+
end
|
80
|
+
|
81
|
+
#
|
82
|
+
# Call inside the run block to denote a data flow
|
83
|
+
#
|
84
|
+
def step(*args)
|
85
|
+
if args[0].is_a?(Hash)
|
86
|
+
hash_based_step(args[0])
|
87
|
+
else
|
88
|
+
single_line_step(args[0])
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
private
|
93
|
+
def initialize(&block)
|
94
|
+
self.block = block
|
95
|
+
super
|
96
|
+
end
|
97
|
+
|
98
|
+
def hash_based_step(*args)
|
99
|
+
source, destination = args[0].first.to_a
|
100
|
+
if destination.is_a?(Array)
|
101
|
+
destination.each { |object| object.input = source.output }
|
102
|
+
else
|
103
|
+
destination.input = source.output
|
104
|
+
end
|
105
|
+
end
|
106
|
+
|
107
|
+
def single_line_step(object)
|
108
|
+
unless @stream
|
109
|
+
@stream = object.output
|
110
|
+
else
|
111
|
+
object.input = @stream
|
112
|
+
@stream = object.output
|
113
|
+
end
|
114
|
+
end
|
115
|
+
end
|
116
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
module Itiel
|
2
|
+
module Load
|
3
|
+
#
|
4
|
+
# This module defines the input and output behavior for Loader steps
|
5
|
+
#
|
6
|
+
# Whenever the instance receives input, it calls persist! and then
|
7
|
+
# wires the input and the output
|
8
|
+
#
|
9
|
+
# All the clasess in Itiel::Output should implement persist!
|
10
|
+
#
|
11
|
+
module ChainedStep
|
12
|
+
module InstanceMethods
|
13
|
+
attr_accessor :next_step
|
14
|
+
|
15
|
+
alias :>> :next_step=
|
16
|
+
|
17
|
+
def input=(input_stream)
|
18
|
+
Itiel::Logger.log_received(self, input_stream.size)
|
19
|
+
persist(input_stream)
|
20
|
+
self.next_step.input = input_stream if next_step
|
21
|
+
Itiel::Logger.log_processed(self, input_stream.size)
|
22
|
+
end
|
23
|
+
|
24
|
+
#
|
25
|
+
# This method must be implemented in the class
|
26
|
+
#
|
27
|
+
def persist(input_stream)
|
28
|
+
raise Itiel::MethodNotImplementedException.new "persist is not implemented"
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def self.included(receiver)
|
33
|
+
receiver.send :include, InstanceMethods
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
require 'csv'
|
2
|
+
|
3
|
+
module Itiel
|
4
|
+
module Load
|
5
|
+
#
|
6
|
+
# Loads the data stream into a CSV file
|
7
|
+
#
|
8
|
+
# Usage:
|
9
|
+
#
|
10
|
+
# @csv_file = Itiel::Load::CSVFile.new('filename.csv')
|
11
|
+
# @csv_file.input = []
|
12
|
+
#
|
13
|
+
class CSVFile
|
14
|
+
include ChainedStep
|
15
|
+
include Itiel::Nameable
|
16
|
+
|
17
|
+
def initialize(file_name, append=true)
|
18
|
+
@append = append
|
19
|
+
@file_name = file_name
|
20
|
+
end
|
21
|
+
|
22
|
+
def persist(input_stream)
|
23
|
+
headers = input_stream.collect(&:keys).flatten.uniq
|
24
|
+
mode = @append ? "ab" : "w"
|
25
|
+
skip_headers = skip_headers?
|
26
|
+
|
27
|
+
CSV.open(@file_name, mode) do |csv|
|
28
|
+
csv << headers unless skip_headers
|
29
|
+
input_stream.each do |row|
|
30
|
+
csv_row = []
|
31
|
+
headers.each do |h|
|
32
|
+
csv_row << row[h]
|
33
|
+
end
|
34
|
+
csv << csv_row
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
private
|
40
|
+
def skip_headers?
|
41
|
+
File.exist?(@file_name) && @append
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
module Itiel
|
2
|
+
module Load
|
3
|
+
#
|
4
|
+
# Loads the stream into a database table.
|
5
|
+
#
|
6
|
+
# Usage:
|
7
|
+
#
|
8
|
+
# @loader = Itiel::Load::DatabaseTable.new :connection, "table_name"
|
9
|
+
#
|
10
|
+
class DatabaseTable
|
11
|
+
include ChainedStep
|
12
|
+
include Itiel::Nameable
|
13
|
+
include Itiel::DB::SQLConnectable
|
14
|
+
|
15
|
+
attr_accessor :table_name
|
16
|
+
|
17
|
+
def initialize(connection, table_name)
|
18
|
+
self.connection = connection
|
19
|
+
self.table_name = table_name
|
20
|
+
end
|
21
|
+
|
22
|
+
def persist(input_stream)
|
23
|
+
input_stream.each do |element|
|
24
|
+
table.insert(element)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def table
|
29
|
+
@@db ||= self.class.sequel_connection(connection)
|
30
|
+
@@db[table_name.to_sym]
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
module Itiel
|
2
|
+
module Load
|
3
|
+
#
|
4
|
+
# This module defines the input and output behavior for Loader steps
|
5
|
+
#
|
6
|
+
# Whenever an Output receives input, it calls persist! and then
|
7
|
+
# wires the input and the output
|
8
|
+
#
|
9
|
+
# All the clasess in Itiel::Output should implement persist!
|
10
|
+
#
|
11
|
+
module ChainedStep
|
12
|
+
module InstanceMethods
|
13
|
+
def input=(input_stream)
|
14
|
+
Itiel::Logger.log_received(self, input_stream.size)
|
15
|
+
persist(input_stream)
|
16
|
+
self.next_step = input_stream if self.next_step
|
17
|
+
Itiel::Logger.log_processed(self, input_stream.size)
|
18
|
+
end
|
19
|
+
|
20
|
+
#
|
21
|
+
# This method has to be implemented in the class
|
22
|
+
#
|
23
|
+
def persist(input_stream)
|
24
|
+
raise "persist is not implemented"
|
25
|
+
end
|
26
|
+
|
27
|
+
private
|
28
|
+
attr_writer :output
|
29
|
+
end
|
30
|
+
|
31
|
+
def self.included(receiver)
|
32
|
+
receiver.send :include, InstanceMethods
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
data/lib/itiel/logger.rb
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
module Itiel
|
2
|
+
class Logger
|
3
|
+
class << self
|
4
|
+
attr_accessor :logger
|
5
|
+
end
|
6
|
+
|
7
|
+
def self.log_received(object, size)
|
8
|
+
msg = "#{object_name(object)} received #{size}.rows"
|
9
|
+
self.log_with_time(msg)
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.log_processed(object, size)
|
13
|
+
msg = "#{object_name(object)} processed #{size}.rows"
|
14
|
+
self.log_with_time(msg)
|
15
|
+
end
|
16
|
+
|
17
|
+
def self.log_start_job(object)
|
18
|
+
msg = "#{object_name(object)} run at #{Time.now}"
|
19
|
+
self.enclosed_with_time(msg)
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.log_end_job(object)
|
23
|
+
msg = "#{object_name(object)} finished at #{Time.now}"
|
24
|
+
self.enclosed_with_time(msg)
|
25
|
+
end
|
26
|
+
|
27
|
+
private
|
28
|
+
def self.object_name(object)
|
29
|
+
( object.respond_to?(:name) ? object.name : object.class.name )
|
30
|
+
end
|
31
|
+
|
32
|
+
def self.info(message)
|
33
|
+
self.logger ||= ::Logger.new(STDOUT)
|
34
|
+
self.logger.info(message)
|
35
|
+
end
|
36
|
+
|
37
|
+
def self.log_with_time(msg)
|
38
|
+
self.info("#{Time.now} - #{msg}")
|
39
|
+
end
|
40
|
+
|
41
|
+
def self.enclosed_with_time(msg)
|
42
|
+
self.info("\n==================================================\n")
|
43
|
+
self.info(msg)
|
44
|
+
self.info("\n==================================================\n")
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|