yarrrml_template_builder 0.1.54
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +8 -0
- data/Changelog.md +1 -0
- data/Gemfile +8 -0
- data/Gemfile.lock +39 -0
- data/LICENSE.txt +21 -0
- data/README.md +139 -0
- data/bin/console +15 -0
- data/bin/setup +8 -0
- data/config/height_yarrrml_template.yaml +190 -0
- data/data/height.csv +2 -0
- data/doc/YARRRMLTemplateBuilder.html +121 -0
- data/doc/YARRRML_Template_Builder.html +6392 -0
- data/doc/YARRRML_Transform.html +1940 -0
- data/doc/_index.html +117 -0
- data/doc/class_list.html +51 -0
- data/doc/css/common.css +1 -0
- data/doc/css/full_list.css +58 -0
- data/doc/css/style.css +497 -0
- data/doc/file.README.html +214 -0
- data/doc/file_list.html +56 -0
- data/doc/frames.html +17 -0
- data/doc/index.html +214 -0
- data/doc/js/app.js +314 -0
- data/doc/js/full_list.js +216 -0
- data/doc/js/jquery.js +4 -0
- data/doc/method_list.html +459 -0
- data/doc/top-level-namespace.html +112 -0
- data/examples/example_output_timerange.rb +56 -0
- data/examples/example_timed_process.rb +56 -0
- data/examples/example_timeinstant_process.rb +56 -0
- data/examples/example_two_linked_processes.rb +88 -0
- data/exemplar_docker_compose.yml +36 -0
- data/lib/yarrrml-template-builder.rb +2 -0
- data/lib/yarrrml_template_builder/version.rb +5 -0
- data/lib/yarrrml_template_builder/yarrrml_template_builder.rb +1485 -0
- data/lib/yarrrml_template_builder/yarrrml_transform.rb +181 -0
- data/lib/yarrrmltemplatebuilder.rb +5 -0
- data/run_me_to_test.rb +26 -0
- data/yarrrml_template_builder.gemspec +39 -0
- metadata +115 -0
@@ -0,0 +1,181 @@
|
|
1
|
+
require 'tempfile'
|
2
|
+
require 'rest-client'
|
3
|
+
|
4
|
+
# note that SDMrdfizer needs to be running on port 4000 with the ./data folder mounted as /data
|
5
|
+
# docker run --name rdfizer --rm -d -p 4000:4000 -v $PWD/data:/data fairdatasystems/sdmrdfizer:0.1.0
|
6
|
+
|
7
|
+
class YARRRML_Transform
|
8
|
+
|
9
|
+
attr_accessor :data_path_server
|
10
|
+
attr_accessor :data_path_client
|
11
|
+
attr_accessor :config_path_server
|
12
|
+
attr_accessor :config_path_client
|
13
|
+
attr_accessor :rdfizer_base_url
|
14
|
+
attr_accessor :yarrrml_transform_base_url
|
15
|
+
attr_accessor :datatype_tag
|
16
|
+
attr_accessor :datafile
|
17
|
+
attr_accessor :baseURI
|
18
|
+
|
19
|
+
attr_accessor :yarrrmltemplate
|
20
|
+
attr_accessor :yarrrmlfilename_client
|
21
|
+
attr_accessor :yarrrmlfilename_server
|
22
|
+
attr_accessor :outputrmlfile
|
23
|
+
attr_accessor :formulation
|
24
|
+
attr_accessor :outputrdffolder
|
25
|
+
attr_accessor :inifile_client
|
26
|
+
attr_accessor :inifile_server
|
27
|
+
attr_accessor :failure
|
28
|
+
|
29
|
+
|
30
|
+
|
31
|
+
# Creates the YARRRML Transformer object
|
32
|
+
#
|
33
|
+
#
|
34
|
+
# the datatype_tag is used to construct other input/output filenames. e.g. a tag of "height" will
|
35
|
+
# cause the output RML file to be "./data/height_rml.ttl", and the expected YARRRML template being named
|
36
|
+
# "./config/height_yarrrml_template.yaml"
|
37
|
+
#
|
38
|
+
# Note that this assumes a specific configuration, with a csv folder mounted as /data/, containing a subdirectory /data/triples
|
39
|
+
# and a folder containing the yarrrml templates mounted as /config inside the docker container
|
40
|
+
#
|
41
|
+
# all params are passed as a hash, and retrieved by params.fetch(paramName). the ini file used by yarrrml transform is auto-generated
|
42
|
+
#
|
43
|
+
# @param params [Hash] params a Hash of options
|
44
|
+
# @option params :datatype_tag [String] (required) a one-word indicator of the data type. This is considered the "base" for all other filenames (see below)
|
45
|
+
# @option params :data_path_server [String] (/data) the path to data from the server perspective (default for Docker image)
|
46
|
+
# @option params :data_path_client [String] (/data) the path to data from the client perspective (default for Docker image)
|
47
|
+
# @option params :config_path_server [String] (/config) the path to config from the server perspective (default for Docker image)
|
48
|
+
# @option params :config_path_client [String] (/config) the path to config from the server perspective (default for Docker image)
|
49
|
+
# @option params :formulation [String] (csv)
|
50
|
+
# @option params :rdfizer_base_url [String] (http://rdfizer:4000) the base URL of the yarrrml_parser (default for a docker)
|
51
|
+
# @option params :yarrrml_transform_base_url [String] ("http://yarrrml_transform:3000") base URL of the yarrrml transform to rml script (default for a docker)
|
52
|
+
|
53
|
+
# @option params :outputrdffolder [String] (/data/triples/) - defaults to /data/triples - this folder must exist, even if left to default. NOTE - this path is not relative to the host, it is relative to the docker rdfizer, so it begins with /data not ./data)
|
54
|
+
# @return [YARRRML_Transform]
|
55
|
+
def initialize(params = {}) # get a name from the "new" call, or set a default
|
56
|
+
|
57
|
+
@datatype_tag = params.fetch( :datatype_tag, nil)
|
58
|
+
unless @datatype_tag
|
59
|
+
warn "must have a datatype_tag parameter. Aborting"
|
60
|
+
self.failure = true
|
61
|
+
return nil
|
62
|
+
end
|
63
|
+
|
64
|
+
@data_path_client = params.fetch(:data_path_client, "/data") # from client perspective (default for docker)
|
65
|
+
@data_path_server = params.fetch(:data_path_server, self.data_path_client) # potentially from Docker image perspective (default for docker)
|
66
|
+
@config_path_client = params.fetch(:config_path_client, "/config") # from client perspective (default for docker)
|
67
|
+
@config_path_server = params.fetch(:config_path_server, self.config_path_client) # potentially from Docker image perspective (default for docker)
|
68
|
+
|
69
|
+
@data_path_client.gsub!('/$', "") # remove trailing slashes -I'll add them later if I need them
|
70
|
+
@data_path_server.gsub!('/$', "")
|
71
|
+
@config_path_client.gsub!('/$', "")
|
72
|
+
@config_path_server.gsub!('/$', "")
|
73
|
+
|
74
|
+
|
75
|
+
@rdfizer_base_url = params.fetch(:rdfizer_base_url, "http://rdfizer:4000")
|
76
|
+
@yarrrml_transform_base_url = params.fetch(:yarrrml_transform_base_url, "http://yarrrml_transform:3000")
|
77
|
+
@rdfizer_base_url.gsub!('/$', "")
|
78
|
+
@yarrrml_transform_base_url.gsub!('/$', "")
|
79
|
+
|
80
|
+
|
81
|
+
@formulation = params.fetch(:formulation, "csv")
|
82
|
+
@datafile = params.fetch(:datafile, "#{self.data_path_server}/#{self.datatype_tag}.csv")
|
83
|
+
@baseURI = params.fetch(:baseURI, ENV['baseURI'])
|
84
|
+
@baseURI = "http://example.org/data/" unless @baseURI
|
85
|
+
|
86
|
+
@outputrdffolder = params.fetch(:outputrdffolder, "#{self.data_path_server}/triples")
|
87
|
+
@outputrmlfile = params.fetch(:outputrmlfile, "#{self.data_path_server}/#{self.datatype_tag}_rml.ttl")
|
88
|
+
@yarrrmlfilename_client = params.fetch(:yarrrmlfilename, "#{self.data_path_client}/#{self.datatype_tag}_yarrrml.yaml")
|
89
|
+
@yarrrmlfilename_server = params.fetch(:yarrrmlfilename, "#{self.data_path_server}/#{self.datatype_tag}_yarrrml.yaml")
|
90
|
+
@yarrrmltemplate = params.fetch(:yarrrmltemplate, "#{self.config_path_client}/#{self.datatype_tag}_yarrrml_template.yaml")
|
91
|
+
@inifile_client = params.fetch(:inifile_client, "#{self.data_path_client}/#{self.datatype_tag}.ini")
|
92
|
+
@inifile_server = params.fetch(:inifile_server, "#{self.data_path_server}/#{self.datatype_tag}.ini") # this will be a docker image in almost all cases
|
93
|
+
|
94
|
+
|
95
|
+
write_ini()
|
96
|
+
|
97
|
+
transform_template()
|
98
|
+
|
99
|
+
return self
|
100
|
+
|
101
|
+
end
|
102
|
+
|
103
|
+
|
104
|
+
|
105
|
+
def transform_template()
|
106
|
+
# transform appropriate template with this data
|
107
|
+
|
108
|
+
File.open(self.yarrrmltemplate, "r") {|f| @template = f.read}
|
109
|
+
@template.gsub!("|||DATA|||", self.datafile)
|
110
|
+
@template.gsub!("|||FORMULATION|||", self.formulation)
|
111
|
+
@template.gsub!("|||BASE|||", self.baseURI)
|
112
|
+
File.open(self.yarrrmlfilename_client, "w") {|f| f.puts @template}
|
113
|
+
warn "Ready to yarrrml transform #{self.datatype_tag} from #{self.yarrrmlfilename_client} "
|
114
|
+
|
115
|
+
end
|
116
|
+
|
117
|
+
|
118
|
+
|
119
|
+
|
120
|
+
def write_ini(inifile = self.inifile_client,
|
121
|
+
path = self.data_path_server,
|
122
|
+
rdffolder = self.outputrdffolder,
|
123
|
+
rmlfile = self.outputrmlfile,
|
124
|
+
datatype = self.datatype_tag)
|
125
|
+
|
126
|
+
configfilecontent = <<CONFIG
|
127
|
+
[default]
|
128
|
+
main_directory: #{path}
|
129
|
+
|
130
|
+
[datasets]
|
131
|
+
number_of_datasets: 1
|
132
|
+
output_folder: #{rdffolder}
|
133
|
+
all_in_one_file: yes
|
134
|
+
remove_duplicate: yes
|
135
|
+
enrichment: yes
|
136
|
+
name: #{datatype}
|
137
|
+
ordered: yes
|
138
|
+
large_file: true
|
139
|
+
|
140
|
+
[dataset1]
|
141
|
+
name: #{datatype}
|
142
|
+
mapping: #{rmlfile}
|
143
|
+
|
144
|
+
CONFIG
|
145
|
+
|
146
|
+
File.open(inifile, "w"){|f| f.puts configfilecontent}
|
147
|
+
|
148
|
+
end
|
149
|
+
|
150
|
+
|
151
|
+
|
152
|
+
# Executes the yarrrml to rml transformation
|
153
|
+
#
|
154
|
+
# no parameters
|
155
|
+
#
|
156
|
+
#
|
157
|
+
def yarrrml_transform
|
158
|
+
warn "running docker yarrrml-parser:ejp-latest"
|
159
|
+
#parser_start_string = "docker run -e PARSERIN=#{self.yarrrmlfilename} -e PARSEROUT=#{self.outputrmlfile} --rm --name yarrrml-parser -v $PWD/data:/data markw/yarrrml-parser-ejp:latest"
|
160
|
+
warn "yarrrml to rml starting with: #{self.yarrrml_transform_base_url} PARSERIN=#{self.yarrrmlfilename_server} -e PARSEROUT=#{self.outputrmlfile}"
|
161
|
+
#resp = RestClient.get("#{self.yarrrml_transform_base_url}/?parserin=#{self.yarrrmlfilename_server}&parserout=#{self.outputrmlfile}")
|
162
|
+
resp = RestClient::Request.execute(method: :get, url: "#{self.yarrrml_transform_base_url}/?parserin=#{self.yarrrmlfilename_server}&parserout=#{self.outputrmlfile}", timeout: 9000000)
|
163
|
+
warn "#{resp}: rml file has been created in #{self.outputrmlfile} - ready to make FAIR data"
|
164
|
+
end
|
165
|
+
|
166
|
+
|
167
|
+
|
168
|
+
# Executes the CSV to RDF based on the RML
|
169
|
+
#
|
170
|
+
# no parameters
|
171
|
+
#
|
172
|
+
#executes the sdmrdfizer transformation using the .ini file created by the 'initialize' routine
|
173
|
+
def make_fair_data
|
174
|
+
warn "making FAIR data with #{self.rdfizer_base_url}/graph_creation/#{self.inifile_server}" # this is sdmrdfizer
|
175
|
+
response = RestClient::Request.execute(method: :get, url: self.rdfizer_base_url + "/graph_creation" + self.inifile_server, timeout: 900000000)
|
176
|
+
warn response.code
|
177
|
+
warn "FAIR data is avaialable in .#{self.outputrdffolder}/#{self.datatype_tag}.nt"
|
178
|
+
end
|
179
|
+
|
180
|
+
|
181
|
+
end
|
data/run_me_to_test.rb
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
#!ruby
|
2
|
+
|
3
|
+
require "yarrrml-template-builder"
|
4
|
+
|
5
|
+
$stderr.puts "this script will do an rdf transformation of the height.csv file, in the ./data folder using the yarrrml file in the ./config folder"
|
6
|
+
$stderr.puts "you must already have the docker-compose up before running this script. If you see failures, that is likely why :-)"
|
7
|
+
datatype_tag = "height" # the "tag" of your data
|
8
|
+
data_path_client = "./data"
|
9
|
+
data_path_server = "/data" # assumes you are running my docker image
|
10
|
+
config_path_client = "./config"
|
11
|
+
config_path_server = "/config" # assumes you are running my docker image
|
12
|
+
rdfizer_base_url = "http://localhost:4000" # again, my docker
|
13
|
+
yarrrml_transform_base_url = "http://localhost:3000" # again, my docker
|
14
|
+
|
15
|
+
y = YARRRML_Transform.new(
|
16
|
+
datatype_tag: datatype_tag,
|
17
|
+
data_path_client: data_path_client,
|
18
|
+
data_path_server: data_path_server,
|
19
|
+
config_path_client: config_path_client,
|
20
|
+
config_path_server: config_path_server,
|
21
|
+
rdfizer_base_url: rdfizer_base_url,
|
22
|
+
yarrrml_transform_base_url: yarrrml_transform_base_url,
|
23
|
+
)
|
24
|
+
y.yarrrml_transform
|
25
|
+
y.make_fair_data
|
26
|
+
|
@@ -0,0 +1,39 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative "lib/yarrrml_template_builder/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "yarrrml_template_builder"
|
7
|
+
spec.version = YARRRMLTemplateBuilder::VERSION
|
8
|
+
spec.authors = ["Mark Wilkinson"]
|
9
|
+
spec.email = ["markw@illuminae.com"]
|
10
|
+
|
11
|
+
spec.summary = "Creates YARRRML Template templates"
|
12
|
+
spec.description = "Creates a templated version of YARRRML, missing the source and iteration type so they can be reused"
|
13
|
+
spec.homepage = "https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder"
|
14
|
+
spec.license = "MIT"
|
15
|
+
spec.required_ruby_version = ">= 2.7.0"
|
16
|
+
|
17
|
+
spec.metadata["allowed_push_host"] = "https://rubygems.org"
|
18
|
+
|
19
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
20
|
+
spec.metadata["source_code_uri"] = "https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder"
|
21
|
+
spec.metadata["changelog_uri"] = "https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder/Changelog.md"
|
22
|
+
|
23
|
+
# Specify which files should be added to the gem when it is released.
|
24
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
25
|
+
spec.files = Dir.chdir(File.expand_path(__dir__)) do
|
26
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features)/}) }
|
27
|
+
end
|
28
|
+
spec.bindir = "exe"
|
29
|
+
spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
|
30
|
+
spec.require_paths = ["lib"]
|
31
|
+
|
32
|
+
# Uncomment to register a new dependency of your gem
|
33
|
+
# spec.add_dependency "example-gem", "~> 1.0"
|
34
|
+
|
35
|
+
spec.add_dependency "yaml", "~> 0.1.0"
|
36
|
+
spec.add_dependency "rest-client", "~> 2.1.0"
|
37
|
+
# For more information and examples about making a new gem, checkout our
|
38
|
+
# guide at: https://bundler.io/guides/creating_gem.html
|
39
|
+
end
|
metadata
ADDED
@@ -0,0 +1,115 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: yarrrml_template_builder
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.54
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Mark Wilkinson
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2022-10-14 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: yaml
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.1.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.1.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rest-client
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 2.1.0
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 2.1.0
|
41
|
+
description: Creates a templated version of YARRRML, missing the source and iteration
|
42
|
+
type so they can be reused
|
43
|
+
email:
|
44
|
+
- markw@illuminae.com
|
45
|
+
executables: []
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- ".gitignore"
|
50
|
+
- Changelog.md
|
51
|
+
- Gemfile
|
52
|
+
- Gemfile.lock
|
53
|
+
- LICENSE.txt
|
54
|
+
- README.md
|
55
|
+
- bin/console
|
56
|
+
- bin/setup
|
57
|
+
- config/height_yarrrml_template.yaml
|
58
|
+
- data/height.csv
|
59
|
+
- doc/YARRRMLTemplateBuilder.html
|
60
|
+
- doc/YARRRML_Template_Builder.html
|
61
|
+
- doc/YARRRML_Transform.html
|
62
|
+
- doc/_index.html
|
63
|
+
- doc/class_list.html
|
64
|
+
- doc/css/common.css
|
65
|
+
- doc/css/full_list.css
|
66
|
+
- doc/css/style.css
|
67
|
+
- doc/file.README.html
|
68
|
+
- doc/file_list.html
|
69
|
+
- doc/frames.html
|
70
|
+
- doc/index.html
|
71
|
+
- doc/js/app.js
|
72
|
+
- doc/js/full_list.js
|
73
|
+
- doc/js/jquery.js
|
74
|
+
- doc/method_list.html
|
75
|
+
- doc/top-level-namespace.html
|
76
|
+
- examples/example_output_timerange.rb
|
77
|
+
- examples/example_timed_process.rb
|
78
|
+
- examples/example_timeinstant_process.rb
|
79
|
+
- examples/example_two_linked_processes.rb
|
80
|
+
- exemplar_docker_compose.yml
|
81
|
+
- lib/yarrrml-template-builder.rb
|
82
|
+
- lib/yarrrml_template_builder/version.rb
|
83
|
+
- lib/yarrrml_template_builder/yarrrml_template_builder.rb
|
84
|
+
- lib/yarrrml_template_builder/yarrrml_transform.rb
|
85
|
+
- lib/yarrrmltemplatebuilder.rb
|
86
|
+
- run_me_to_test.rb
|
87
|
+
- yarrrml_template_builder.gemspec
|
88
|
+
homepage: https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder
|
89
|
+
licenses:
|
90
|
+
- MIT
|
91
|
+
metadata:
|
92
|
+
allowed_push_host: https://rubygems.org
|
93
|
+
homepage_uri: https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder
|
94
|
+
source_code_uri: https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder
|
95
|
+
changelog_uri: https://github.com/ejp-rd-vp/CDE-semantic-model-implementations/tree/master/YARRRML_Tools/yarrrml_template_builder/Changelog.md
|
96
|
+
post_install_message:
|
97
|
+
rdoc_options: []
|
98
|
+
require_paths:
|
99
|
+
- lib
|
100
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
101
|
+
requirements:
|
102
|
+
- - ">="
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: 2.7.0
|
105
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - ">="
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
requirements: []
|
111
|
+
rubygems_version: 3.2.28
|
112
|
+
signing_key:
|
113
|
+
specification_version: 4
|
114
|
+
summary: Creates YARRRML Template templates
|
115
|
+
test_files: []
|