chronicle-etl 0.1.2 → 0.2.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.rubocop.yml +8 -0
- data/.ruby-version +1 -0
- data/.yardopts +1 -0
- data/CHANGELOG.md +11 -0
- data/Gemfile.lock +42 -10
- data/README.md +64 -11
- data/bin/console +16 -4
- data/chronicle-etl.gemspec +8 -6
- data/exe/chronicle-etl +2 -2
- data/lib/chronicle/etl.rb +6 -2
- data/lib/chronicle/etl/catalog.rb +102 -0
- data/lib/chronicle/etl/cli/connectors.rb +32 -0
- data/lib/chronicle/etl/cli/jobs.rb +110 -0
- data/lib/chronicle/etl/cli/main.rb +83 -0
- data/lib/chronicle/etl/cli/subcommand_base.rb +37 -0
- data/lib/chronicle/etl/config.rb +32 -0
- data/lib/chronicle/etl/exceptions.rb +17 -0
- data/lib/chronicle/etl/extractors/{csv.rb → csv_extractor.rb} +3 -3
- data/lib/chronicle/etl/extractors/extractor.rb +23 -12
- data/lib/chronicle/etl/extractors/file_extractor.rb +52 -0
- data/lib/chronicle/etl/extractors/stdin_extractor.rb +11 -0
- data/lib/chronicle/etl/loaders/csv_loader.rb +29 -0
- data/lib/chronicle/etl/loaders/loader.rb +23 -16
- data/lib/chronicle/etl/loaders/rest_loader.rb +30 -0
- data/lib/chronicle/etl/loaders/stdout_loader.rb +9 -0
- data/lib/chronicle/etl/loaders/table_loader.rb +21 -0
- data/lib/chronicle/etl/runner.rb +27 -38
- data/lib/chronicle/etl/transformers/json_transformer.rb +11 -0
- data/lib/chronicle/etl/transformers/null_transformer.rb +10 -0
- data/lib/chronicle/etl/transformers/transformer.rb +28 -11
- data/lib/chronicle/etl/utils/progress_bar.rb +76 -0
- data/lib/chronicle/etl/version.rb +2 -2
- metadata +68 -29
- data/lib/chronicle/etl/cli.rb +0 -38
- data/lib/chronicle/etl/extractors/stdin.rb +0 -13
- data/lib/chronicle/etl/loaders/csv.rb +0 -31
- data/lib/chronicle/etl/loaders/stdout.rb +0 -11
- data/lib/chronicle/etl/loaders/table.rb +0 -22
- data/lib/chronicle/etl/transformers/json.rb +0 -13
- data/lib/chronicle/etl/transformers/null.rb +0 -11
- data/lib/chronicle/etl/utils/progress_bar_wrapper.rb +0 -43
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e1c08bc4f71c807525090abbf1701be19ab72cce08a99cc3bbec9b0db7150a02
|
4
|
+
data.tar.gz: 172a5d7e7ba7a9424ef7b5ab4da2b8c44defdb4e0a34c833248ff1b63f40407e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0f671c00928b15f9c0f6fa159ac106ff9c4f65a8bd16048e5d0cab82d680945317f7680e7796e98c665bb5cc757e0657f1a36d773d89e3e1587d9eebc12abdd8
|
7
|
+
data.tar.gz: 449d1368e0054f39006c7903218300b9b97ca839d6eff43b6b7bd659e5146d443a31c53325c4769ae7a56db9d42417020ccde17362ae024c01aca2ed63029044
|
data/.rubocop.yml
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.7.1
|
data/.yardopts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--markup=markdown
|
data/CHANGELOG.md
CHANGED
@@ -2,6 +2,17 @@
|
|
2
2
|
|
3
3
|
This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
4
4
|
|
5
|
+
## [0.1.4] - 2020-08-18
|
6
|
+
### Updated
|
7
|
+
- Better display of available ETL classes
|
8
|
+
- Updated documentation
|
9
|
+
|
10
|
+
## [0.1.3] - 2020-08-13
|
11
|
+
### Added
|
12
|
+
- Ability to list all available ETL classes
|
13
|
+
- Refactored E, T, L module and class structure
|
14
|
+
- Better progress bar
|
15
|
+
|
5
16
|
## [0.1.2] - 2020-08-02
|
6
17
|
### Added
|
7
18
|
- This changelog
|
data/Gemfile.lock
CHANGED
@@ -1,11 +1,11 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
chronicle-etl (0.
|
4
|
+
chronicle-etl (0.2.2)
|
5
5
|
colorize (~> 0.8.1)
|
6
|
-
ruby-progressbar (~> 1.10)
|
7
|
-
table_print
|
8
6
|
thor (~> 0.20)
|
7
|
+
tty-progressbar (~> 0.17)
|
8
|
+
tty-table (~> 0.11)
|
9
9
|
|
10
10
|
GEM
|
11
11
|
remote: https://rubygems.org/
|
@@ -14,14 +14,21 @@ GEM
|
|
14
14
|
coderay (1.1.3)
|
15
15
|
colorize (0.8.1)
|
16
16
|
diff-lcs (1.4.4)
|
17
|
+
equatable (0.6.1)
|
17
18
|
method_source (1.0.0)
|
19
|
+
necromancer (0.6.0)
|
20
|
+
pastel (0.7.4)
|
21
|
+
equatable (~> 0.6)
|
22
|
+
tty-color (~> 0.5)
|
18
23
|
pry (0.13.1)
|
19
24
|
coderay (~> 1.1)
|
20
25
|
method_source (~> 1.0)
|
21
26
|
pry-byebug (3.9.0)
|
22
27
|
byebug (~> 11.0)
|
23
28
|
pry (~> 0.13.0)
|
24
|
-
rake (
|
29
|
+
rake (13.0.1)
|
30
|
+
redcarpet (3.5.0)
|
31
|
+
refinements (7.7.0)
|
25
32
|
rspec (3.9.0)
|
26
33
|
rspec-core (~> 3.9.0)
|
27
34
|
rspec-expectations (~> 3.9.0)
|
@@ -35,19 +42,44 @@ GEM
|
|
35
42
|
diff-lcs (>= 1.2.0, < 2.0)
|
36
43
|
rspec-support (~> 3.9.0)
|
37
44
|
rspec-support (3.9.3)
|
38
|
-
|
39
|
-
|
45
|
+
runcom (6.2.0)
|
46
|
+
refinements (~> 7.4)
|
47
|
+
xdg (~> 4.0)
|
48
|
+
strings (0.1.8)
|
49
|
+
strings-ansi (~> 0.1)
|
50
|
+
unicode-display_width (~> 1.5)
|
51
|
+
unicode_utils (~> 1.4)
|
52
|
+
strings-ansi (0.1.0)
|
40
53
|
thor (0.20.3)
|
54
|
+
tty-color (0.5.2)
|
55
|
+
tty-cursor (0.7.1)
|
56
|
+
tty-progressbar (0.17.0)
|
57
|
+
strings-ansi (~> 0.1.0)
|
58
|
+
tty-cursor (~> 0.7)
|
59
|
+
tty-screen (~> 0.7)
|
60
|
+
unicode-display_width (~> 1.6)
|
61
|
+
tty-screen (0.8.1)
|
62
|
+
tty-table (0.11.0)
|
63
|
+
equatable (~> 0.6)
|
64
|
+
necromancer (~> 0.5)
|
65
|
+
pastel (~> 0.7.2)
|
66
|
+
strings (~> 0.1.5)
|
67
|
+
tty-screen (~> 0.7)
|
68
|
+
unicode-display_width (1.7.0)
|
69
|
+
unicode_utils (1.4.0)
|
70
|
+
xdg (4.2.0)
|
41
71
|
|
42
72
|
PLATFORMS
|
43
73
|
ruby
|
44
74
|
|
45
75
|
DEPENDENCIES
|
46
|
-
bundler (~> 1
|
76
|
+
bundler (~> 2.1)
|
47
77
|
chronicle-etl!
|
48
78
|
pry-byebug (~> 3.9)
|
49
|
-
rake (~>
|
50
|
-
|
79
|
+
rake (~> 13.0)
|
80
|
+
redcarpet (~> 3.5)
|
81
|
+
rspec (~> 3.9)
|
82
|
+
runcom (~> 6.2)
|
51
83
|
|
52
84
|
BUNDLED WITH
|
53
|
-
1.
|
85
|
+
2.1.4
|
data/README.md
CHANGED
@@ -1,6 +1,10 @@
|
|
1
|
-
# Chronicle::
|
1
|
+
# Chronicle::ETL
|
2
2
|
|
3
|
-
|
3
|
+
[](https://badge.fury.io/rb/chronicle-etl)
|
4
|
+
|
5
|
+
Chronicle ETL is a utility tool for archiving and processing personal data. You can extract it from a variety of source, transform it, and load it to different APIs or file formats.
|
6
|
+
|
7
|
+
This project is an adaptation of Andrew Louis's experimental [Memex project](https://hyfen.net/memex).
|
4
8
|
|
5
9
|
## Installation
|
6
10
|
|
@@ -8,28 +12,77 @@ Chronicle ETL is a utility tool for manipulating personal data. You can extract
|
|
8
12
|
$ gem install chronicle-etl
|
9
13
|
```
|
10
14
|
|
11
|
-
##
|
15
|
+
## Usage
|
12
16
|
|
13
17
|
After installing the gem, `chronicle-etl` is available to run in your shell.
|
14
18
|
|
19
|
+
```bash
|
20
|
+
# read test.csv and display it as a table
|
21
|
+
$ chronicle-etl jobs:run --extractor csv --extractor-opts filename:test.csv --loader table
|
22
|
+
|
23
|
+
# Display help for the jobs:run command
|
24
|
+
$ chronicle-etl jobs help run
|
15
25
|
```
|
16
|
-
|
17
|
-
|
26
|
+
|
27
|
+
## Connectors
|
28
|
+
|
29
|
+
Connectors are available to read, process, and load data from different formats or external services.
|
30
|
+
|
31
|
+
```bash
|
32
|
+
# List all available connectors
|
33
|
+
$ chronicle-etl connectors:list
|
18
34
|
```
|
19
35
|
|
20
|
-
|
36
|
+
Built in connectors:
|
37
|
+
|
38
|
+
### Extractors
|
39
|
+
- `stdin` - (default) Load records from line-separated stdin
|
40
|
+
- `csv`
|
41
|
+
- `file` - load from a single file or directory (with a glob pattern)
|
42
|
+
|
43
|
+
### Transformers
|
44
|
+
- `null` - (default) Don't do anything
|
45
|
+
|
46
|
+
### Loaders
|
47
|
+
- `stdout` - (default) output transformed records to stdount
|
48
|
+
- `csv` - Load records to a csv file
|
49
|
+
- `table` - Output an ascii table of records. Useful for debugging.
|
50
|
+
|
51
|
+
### Provider-specific importers
|
52
|
+
|
53
|
+
In addition to the built-in importers, importers for third-party platforms are available. They are packaged as individual Ruby gems.
|
54
|
+
|
55
|
+
- [email](https://github.com/chronicle-app/chronicle-email). Extractors for `mbox` files. Transformers for chronicle schema
|
56
|
+
- [bash](https://github.com/chronicle-app/chronicle-bash). Extract bash history from `~/.bash_history`. Transform it for chronicle schema
|
57
|
+
|
58
|
+
To install any of these, run `gem install chronicle-PROVIDER`.
|
59
|
+
|
60
|
+
If you don't want to use the available rubygem importers, `chronicle-etl` can use `stdin` as an Extractor source (newline separated records). You can also use `stdout` as a loader — transformed records will be outputted separated by newlines.
|
61
|
+
|
62
|
+
I'll be open-sourcing more importers. Please [contact me](mailto:andrew@hyfen.net) to chat about what will be available!
|
63
|
+
|
64
|
+
### Full commands
|
21
65
|
|
22
66
|
```
|
23
|
-
|
24
|
-
|
25
|
-
|
67
|
+
$ chronicle-etl help
|
68
|
+
|
69
|
+
ALL COMMANDS
|
70
|
+
help # This help menu
|
71
|
+
connectors help [COMMAND] # Describe subcommands or one specific subcommand
|
72
|
+
connectors:install NAME # Installs connector NAME
|
73
|
+
connectors:list # Lists available connectors
|
74
|
+
jobs help [COMMAND] # Describe subcommands or one specific subcommand
|
75
|
+
jobs:create # Create a job
|
76
|
+
jobs:list # List all available jobs
|
77
|
+
jobs:run # Start a job
|
78
|
+
jobs:show # Show a job
|
26
79
|
```
|
27
80
|
|
28
81
|
### Job options
|
29
82
|
|
30
83
|
```
|
31
84
|
Usage:
|
32
|
-
chronicle-etl
|
85
|
+
chronicle-etl jobs:run
|
33
86
|
|
34
87
|
Options:
|
35
88
|
-e, [--extractor=extractor-name] # Extractor class (available: stdin, csv, file)
|
@@ -62,4 +115,4 @@ The gem is available as open source under the terms of the [MIT License](https:/
|
|
62
115
|
|
63
116
|
## Code of Conduct
|
64
117
|
|
65
|
-
Everyone interacting in the Chronicle::
|
118
|
+
Everyone interacting in the Chronicle::ETL project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/chronicle-app/chronicle-etl/blob/master/CODE_OF_CONDUCT.md).
|
data/bin/console
CHANGED
@@ -7,8 +7,20 @@ require "chronicle/etl"
|
|
7
7
|
# with your gem easier. You can also use a different console, if you like.
|
8
8
|
|
9
9
|
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
-
|
11
|
-
|
10
|
+
require "pry"
|
11
|
+
Pry.start
|
12
|
+
|
13
|
+
def reload!(print = true)
|
14
|
+
puts 'Reloading ...' if print
|
15
|
+
# Main project directory.
|
16
|
+
root_dir = File.expand_path('..', __dir__)
|
17
|
+
# Directories within the project that should be reloaded.
|
18
|
+
reload_dirs = %w{lib}
|
19
|
+
# Loop through and reload every file in all relevant project directories.
|
20
|
+
reload_dirs.each do |dir|
|
21
|
+
Dir.glob("#{root_dir}/#{dir}/**/*.rb").each { |f| load(f) }
|
22
|
+
end
|
23
|
+
# Return true when complete.
|
24
|
+
true
|
25
|
+
end
|
12
26
|
|
13
|
-
require "irb"
|
14
|
-
IRB.start(__FILE__)
|
data/chronicle-etl.gemspec
CHANGED
@@ -5,7 +5,7 @@ require "chronicle/etl/version"
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |spec|
|
7
7
|
spec.name = "chronicle-etl"
|
8
|
-
spec.version = Chronicle::
|
8
|
+
spec.version = Chronicle::ETL::VERSION
|
9
9
|
spec.authors = ["Andrew Louis"]
|
10
10
|
spec.email = ["andrew@hyfen.net"]
|
11
11
|
|
@@ -38,11 +38,13 @@ Gem::Specification.new do |spec|
|
|
38
38
|
|
39
39
|
spec.add_dependency "thor", "~> 0.20"
|
40
40
|
spec.add_dependency "colorize", "~> 0.8.1"
|
41
|
-
spec.add_dependency "
|
42
|
-
spec.add_dependency "
|
41
|
+
spec.add_dependency "tty-table", "~> 0.11"
|
42
|
+
spec.add_dependency "tty-progressbar", "~> 0.17"
|
43
43
|
|
44
|
-
spec.add_development_dependency "bundler", "~> 1
|
45
|
-
spec.add_development_dependency "rake", "~>
|
46
|
-
spec.add_development_dependency "rspec", "~> 3.
|
44
|
+
spec.add_development_dependency "bundler", "~> 2.1"
|
45
|
+
spec.add_development_dependency "rake", "~> 13.0"
|
46
|
+
spec.add_development_dependency "rspec", "~> 3.9"
|
47
47
|
spec.add_development_dependency "pry-byebug", "~> 3.9"
|
48
|
+
spec.add_development_dependency 'runcom', '~> 6.2'
|
49
|
+
spec.add_development_dependency 'redcarpet', '~> 3.5'
|
48
50
|
end
|
data/exe/chronicle-etl
CHANGED
data/lib/chronicle/etl.rb
CHANGED
@@ -1,5 +1,9 @@
|
|
1
|
+
require_relative 'etl/catalog'
|
2
|
+
require_relative 'etl/config'
|
3
|
+
require_relative 'etl/exceptions'
|
1
4
|
require_relative 'etl/extractors/extractor'
|
2
|
-
require_relative 'etl/transformers/transformer'
|
3
5
|
require_relative 'etl/loaders/loader'
|
4
|
-
require_relative 'etl/utils/progress_bar_wrapper'
|
5
6
|
require_relative 'etl/runner'
|
7
|
+
require_relative 'etl/transformers/transformer'
|
8
|
+
require_relative 'etl/utils/progress_bar'
|
9
|
+
require_relative 'etl/version'
|
@@ -0,0 +1,102 @@
|
|
1
|
+
module Chronicle
|
2
|
+
module ETL
|
3
|
+
# Utility methods to catalogue which Extractor, Transformer, and
|
4
|
+
# Loader connector classes are available to chronicle-etl
|
5
|
+
module Catalog
|
6
|
+
PLUGINS = ['email', 'bash']
|
7
|
+
BUILTIN = {
|
8
|
+
extractor: ['stdin', 'json', 'csv', 'file'],
|
9
|
+
transformer: ['null'],
|
10
|
+
loader: ['stdout', 'csv', 'table', 'rest']
|
11
|
+
}.freeze
|
12
|
+
|
13
|
+
# Return which ETL connectors are available, both built in and externally-defined
|
14
|
+
def self.available_classes
|
15
|
+
# TODO: have a registry of plugins
|
16
|
+
|
17
|
+
# Attempt to load each chronicle plugin that we might know about so
|
18
|
+
# that we can later search for subclasses to build our list of
|
19
|
+
# available classes
|
20
|
+
PLUGINS.each do |plugin|
|
21
|
+
require "chronicle/#{plugin}"
|
22
|
+
rescue LoadError
|
23
|
+
# this will happen if the gem isn't available globally
|
24
|
+
end
|
25
|
+
|
26
|
+
parent_klasses = [
|
27
|
+
::Chronicle::ETL::Extractor,
|
28
|
+
::Chronicle::ETL::Transformer,
|
29
|
+
::Chronicle::ETL::Loader
|
30
|
+
]
|
31
|
+
klasses = []
|
32
|
+
parent_klasses.map do |parent|
|
33
|
+
klasses += ::ObjectSpace.each_object(::Class).select { |klass| klass < parent }
|
34
|
+
end
|
35
|
+
|
36
|
+
klasses.map do |klass|
|
37
|
+
{
|
38
|
+
name: klass.name,
|
39
|
+
built_in: klass.built_in?,
|
40
|
+
provider: klass.provider,
|
41
|
+
phase: klass.phase
|
42
|
+
}
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
# For a given connector identifier, return the class (either builtin, or from a
|
47
|
+
# external chronicle gem)
|
48
|
+
def self.identifier_to_klass(identifier:, phase:)
|
49
|
+
if BUILTIN[phase].include? identifier
|
50
|
+
load_builtin_klass(name: identifier, phase: phase)
|
51
|
+
else
|
52
|
+
provider, name = identifier.split(':')
|
53
|
+
name ||= ''
|
54
|
+
load_provider_klass(provider: provider, name: name, phase: phase)
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
# Returns whether a class is an Extractor, Transformer, or Loader
|
59
|
+
def phase
|
60
|
+
ancestors = self.ancestors
|
61
|
+
return :extractor if ancestors.include? Chronicle::ETL::Extractor
|
62
|
+
return :transformer if ancestors.include? Chronicle::ETL::Transformer
|
63
|
+
return :loader if ancestors.include? Chronicle::ETL::Loader
|
64
|
+
end
|
65
|
+
|
66
|
+
# Returns which third-party provider this connector is associated wtih
|
67
|
+
def provider
|
68
|
+
# TODO: needs better convention for a gem reporting its provider name
|
69
|
+
provider = to_s.split('::')[1].downcase
|
70
|
+
provider == 'etl' ? 'chronicle' : provider
|
71
|
+
end
|
72
|
+
|
73
|
+
# Returns whether this connector is a built-in one
|
74
|
+
def built_in?
|
75
|
+
to_s.include? 'Chronicle::ETL'
|
76
|
+
end
|
77
|
+
|
78
|
+
private
|
79
|
+
|
80
|
+
def self.load_builtin_klass(name:, phase:)
|
81
|
+
klass_str = "Chronicle::ETL::#{name.capitalize}#{phase.capitalize}"
|
82
|
+
begin
|
83
|
+
Object.const_get(klass_str)
|
84
|
+
rescue NameError => e
|
85
|
+
raise ConnectorNotAvailableError.new("Connector not found", name: name)
|
86
|
+
end
|
87
|
+
end
|
88
|
+
|
89
|
+
def self.load_provider_klass(name: '', phase:, provider:)
|
90
|
+
begin
|
91
|
+
require "chronicle/#{provider}"
|
92
|
+
klass_str = "Chronicle::#{provider.capitalize}::#{name.capitalize}#{phase.capitalize}"
|
93
|
+
Object.const_get(klass_str)
|
94
|
+
rescue LoadError => e
|
95
|
+
raise ProviderNotAvailableError.new("Provider '#{provider.capitalize}' could not be loaded", provider: provider)
|
96
|
+
rescue NameError => e
|
97
|
+
raise ProviderConnectorNotAvailableError.new("Connector '#{name}' in '#{provider}' could not be found", provider: provider, name: name)
|
98
|
+
end
|
99
|
+
end
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
module Chronicle
|
2
|
+
module ETL
|
3
|
+
module CLI
|
4
|
+
# CLI commands for working with ETL connectors
|
5
|
+
class Connectors < SubcommandBase
|
6
|
+
default_task 'list'
|
7
|
+
namespace :connectors
|
8
|
+
|
9
|
+
desc "install NAME", "Installs connector NAME"
|
10
|
+
def install
|
11
|
+
puts "Installing"
|
12
|
+
end
|
13
|
+
|
14
|
+
desc "list", "Lists available connectors"
|
15
|
+
# Display all available connectors that chronicle-etl has access to
|
16
|
+
def list
|
17
|
+
klasses = Chronicle::ETL::Catalog.available_classes
|
18
|
+
klasses = klasses.sort_by do |a|
|
19
|
+
[a[:built_in].to_s, a[:provider], a[:phase]]
|
20
|
+
end
|
21
|
+
|
22
|
+
headers = klasses.first.keys.map do |key|
|
23
|
+
key.to_s.upcase.bold
|
24
|
+
end
|
25
|
+
|
26
|
+
table = TTY::Table.new(headers, klasses.map(&:values))
|
27
|
+
puts table.render(indent: 0, padding: [0, 2])
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|