tc211-termbase 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 595681dcffbabcec368f07c06712468fb8d124e4183355bed7d610ed9aac6caf
+  data.tar.gz: '017583476a0a5743adedf8cefa49e2b657eb7e6686133b8be5c95d72fce02dc2'
+SHA512:
+  metadata.gz: 24ea15ba4f0c8bad6b963d0765f793ff2578dd2c1373e75adcbafacc4e9cafe1e35fdbadbc61a2d2f7d06dc1ec531c759615fc50edc93b66e3383a1ffe14b56d
+  data.tar.gz: b7eb57174f742c5afe931232c61415def36d62218deba71fce24d39596d08ddf08c9835b71c9caf6d290c66b06290c0f37cb1d44b6abf178aefa06b7c2564ff4

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,7 @@
+---
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+  - 2.4.3
+before_install: gem install bundler -v 1.17.1

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at ronald.tse@ribose.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in tc211-termbase.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,63 @@
+PATH
+  remote: .
+  specs:
+    tc211-termbase (0.1.0)
+      creek
+      iso-639
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.5.2)
+      public_suffix (>= 2.0.2, < 4.0)
+    creek (2.4.1)
+      http (~> 3.0)
+      nokogiri (>= 1.7.0)
+      rubyzip (>= 1.0.0)
+    diff-lcs (1.3)
+    domain_name (0.5.20180417)
+      unf (>= 0.0.5, < 1.0.0)
+    http (3.3.0)
+      addressable (~> 2.3)
+      http-cookie (~> 1.0)
+      http-form_data (~> 2.0)
+      http_parser.rb (~> 0.6.0)
+    http-cookie (1.0.3)
+      domain_name (~> 0.5)
+    http-form_data (2.1.1)
+    http_parser.rb (0.6.0)
+    iso-639 (0.2.8)
+    mini_portile2 (2.3.0)
+    nokogiri (1.8.5)
+      mini_portile2 (~> 2.3.0)
+    public_suffix (3.0.3)
+    rake (10.5.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.0)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-mocks (3.8.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.0)
+    rubyzip (1.2.2)
+    unf (0.1.4)
+      unf_ext
+    unf_ext (0.0.7.5)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.17)
+  rake (~> 10.0)
+  rspec (~> 3.0)
+  tc211-termbase!
+
+BUNDLED WITH
+   1.17.1

data/README.adoc

@@ -0,0 +1,37 @@
+= Tc211::Termbase
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/tc211/termbase`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+== Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'tc211-termbase'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install tc211-termbase
+
+== Usage
+
+TODO: Write usage instructions here
+
+== Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+== Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/riboseinc/tc211-termbase. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+== Code of Conduct
+
+Everyone interacting in the Tc211::Termbase project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/riboseinc/tc211-termbase/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "tc211/termbase"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/exe/tc211-termbase-xlsx2yaml

@@ -0,0 +1,67 @@
+#!/usr/bin/env ruby
+
+require 'creek'
+require 'pp'
+require 'pathname'
+require 'fileutils'
+require_relative '../lib/tc211/termbase.rb'
+# require 'pry'
+
+filepath = ARGV[0]
+#'./tc211-termbase.xlsx'
+
+if filepath.nil?
+  puts 'Error: no filepath given as first argument.'
+  exit 1
+end
+
+if Pathname.new(filepath).extname != ".xlsx"
+  puts 'Error: filepath given must have extension .xlsx.'
+  exit 1
+end
+
+
+workbook = Tc211::Termbase::TermWorkbook.new(filepath)
+workbook.glossary_info.metadata_section.structure
+workbook.glossary_info.metadata_section.attributes
+
+languages = {}
+
+workbook.languages_supported.map do |lang|
+  puts "************** WORKING ON LANGUAGE (#{lang})"
+  sheet = workbook.language_sheet(lang)
+  termsec = sheet.terms_section
+  languages[sheet.language_code] = termsec.terms
+end
+
+collection = Tc211::Termbase::ConceptCollection.new
+
+languages.each_pair do |lang, terms|
+  terms.each do |term|
+    collection.add_term(term)
+  end
+end
+
+# collection[1206].inspect
+
+output_dir = Dir.pwd
+
+collection.to_file(File.join(output_dir, Pathname.new(filepath).basename.sub_ext(".yaml")))
+
+collection_output_dir = File.join(output_dir, "concepts")
+
+FileUtils.mkdir_p(collection_output_dir)
+
+collection.keys.each do |id|
+  collection[id].to_file(File.join(collection_output_dir, "concept-#{id}.yaml"))
+end
+
+# french = workbook.language_sheet("French")
+# french.sections[3].structure
+# french.sections[3].terms
+
+# english = workbook.language_sheet("English")
+# english.terms_section
+# english.terms_section.terms
+
+#pry.binding

data/lib/tc211/termbase.rb

@@ -0,0 +1,11 @@
+require "tc211/termbase/version"
+
+module Tc211
+  module Termbase
+    class Error < StandardError; end
+    # Your code goes here...
+  end
+end
+
+require 'tc211/termbase/term_workbook'
+require 'tc211/termbase/concept_collection'

data/lib/tc211/termbase/concept.rb

@@ -0,0 +1,35 @@
+module Tc211::Termbase
+
+class Concept < Hash
+  attr_accessor :id
+  attr_accessor :terms
+
+  def initialize(options={})
+    terms = options.delete(:terms) || []
+    terms.each do |term|
+      add_term(term)
+    end
+
+    options.each_pair do |k,v|
+      self.send("#{k}=", v)
+    end
+  end
+
+  def add_term(term)
+    self[term.language_code] = term
+  end
+
+  def to_hash
+    self.inject({}) do |acc, (lang, term)|
+      acc.merge!(lang => term.to_hash)
+    end
+  end
+
+  def to_file(filename)
+    File.open(filename,"w") do |file|
+      file.write(to_hash.to_yaml)
+    end
+  end
+
+end
+end

data/lib/tc211/termbase/concept_collection.rb

@@ -0,0 +1,32 @@
+require_relative "concept"
+
+module Tc211::Termbase
+
+class ConceptCollection < Hash
+
+  def add_term(term)
+    if self[term.id]
+      self[term.id].add_term(term)
+    else
+      self[term.id] = Concept.new(
+        id: term.id,
+        terms: [term]
+      )
+    end
+  end
+
+  def to_hash
+    self.inject({}) do |acc, (id, concept)|
+      acc.merge!(id => concept.to_hash)
+    end
+  end
+
+  def to_file(filename)
+    File.open(filename,"w") do |file|
+      file.write(to_hash.to_yaml)
+    end
+  end
+
+end
+
+end

data/lib/tc211/termbase/information_sheet.rb

@@ -0,0 +1,22 @@
+require_relative "terminology_sheet"
+
+module Tc211::Termbase
+
+class InformationSheet < TerminologySheet
+
+  def metadata_section
+    sheet_array = @sheet.simple_rows.to_a
+    section = MetadataSection.new(sheet_array)
+  end
+
+  def to_hash
+    { "glossary" => metadata_section.to_hash }
+  end
+
+  def to_yaml
+    to_hash.to_yaml
+  end
+
+end
+
+end

data/lib/tc211/termbase/metadata_section.rb

@@ -0,0 +1,87 @@
+require_relative "sheet_section"
+
+module Tc211::Termbase
+
+class MetadataSection < SheetSection
+  attr_accessor :header_row
+  attr_accessor :attributes
+
+  GLOSSARY_HEADER_ROW_MATCH = {
+    "A" => [nil, "Item", "A"], # "Arabic" uses "A"
+    "C" => ["Data Type"],
+    "D" => ["Special Instruction"],
+    "E" => ["ISO 19135 Class.attribute"],
+    "F" => ["Domain"]
+  }
+
+  GLOSSARY_ROW_KEY_MAP = {
+    "A" => "name",
+    "B" => "value",
+    "C" => "datatype",
+    "D" => "special-instruction",
+    "E" => "19135-class-attribute",
+    "F" => "value-domain"
+  }
+
+  def initialize(rows, options={})
+    super
+    raise unless self.class.match_header(@rows[0])
+    @header_row = @rows[0]
+    @body_rows = @rows[1..-1]
+    attributes
+    self
+  end
+
+  def self.match_header(row)
+    puts "row #{row}"
+    row.inject(true) do |acc, (key, value)|
+      puts "#{key}, #{value}"
+      if GLOSSARY_HEADER_ROW_MATCH[key]
+        acc && GLOSSARY_HEADER_ROW_MATCH[key].include?(value)
+      else
+        acc
+      end
+    end
+  end
+
+  def structure
+    GLOSSARY_ROW_KEY_MAP
+  end
+
+  def parse_row(row)
+    return nil if row.empty?
+    attribute = {}
+
+    structure.each_pair do |key, value|
+      puts "#{key}, #{value}, #{row[key]}"
+      attribute_key = value
+      attribute_value = row[key]
+      next if attribute_value.nil?
+      attribute[attribute_key] = attribute_value
+    end
+
+    # TODO: "Chinese" name is empty!
+    key = (attribute["name"] || "(empty)").downcase.split(" ").join("-")
+
+    { key => attribute }
+  end
+
+  def attributes
+    return @attributes if @attributes
+
+    @attributes = {}
+    @body_rows.each do |row|
+      result = parse_row(row)
+      @attributes.merge!(result) if result
+    end
+    @attributes
+  end
+
+  def to_hash
+    {
+      "metadata" => attributes
+    }
+  end
+
+end
+end

data/lib/tc211/termbase/sheet_section.rb

@@ -0,0 +1,26 @@
+
+module Tc211::Termbase
+
+class SheetSection
+  attr_accessor :sheet_content
+
+  def initialize(rows, options={})
+    # rows is an array of rows!
+    raise unless rows.is_a?(Array)
+    @rows = rows
+    # @has_header = options[:has_header].nil? ? true : options[:has_header]
+    self
+  end
+
+  # Abstract method
+  def self.match_header(row)
+    false
+  end
+
+  def self.identify_type(row)
+
+  end
+
+  # TODO
+end
+end

data/lib/tc211/termbase/term.rb

@@ -0,0 +1,136 @@
+module Tc211::Termbase
+
+class Term
+
+  ATTRIBS = %i(
+    id term abbrev synonyms alt definition
+    country_code
+    language_code
+    notes examples
+    entry_status
+    classification
+    review_indicator
+    authoritative_source
+    authoritative_source_similarity
+    lineage_source
+    lineage_source_similarity
+    date_accepted
+    date_amended
+    review_date
+    review_status
+    review_type
+    review_decision
+    review_decision_date
+    review_decision_event
+    review_decision_notes
+    release
+  )
+
+  attr_accessor *ATTRIBS
+
+  def initialize(options={})
+    @examples = []
+    @notes = []
+
+    puts "options #{options.inspect}"
+
+    options.each_pair do |k, v|
+      next unless v
+      case k
+      when /^example/
+        @examples << v
+      when /^note/
+        @notes << v
+      else
+        puts "Key #{k}"
+        key = k.gsub("-", "_")
+        self.send("#{key}=", v)
+      end
+    end
+    self
+  end
+
+  def to_hash
+    ATTRIBS.inject({}) do |acc, attrib|
+      value = self.send(attrib)
+      unless value.nil?
+        acc.merge(attrib => value)
+      else
+        acc
+      end
+    end
+  end
+
+  # entry-status
+  ## Must be one of notValid valid superseded retired
+  def entry_status=(value)
+    unless %w(notValid valid superseded retired).include?(value)
+      value = "notValid"
+    end
+    @entry_status = value
+  end
+
+  # classification
+  ## Must be one of the following: preferred admitted deprecated
+  def classification=(value)
+    unless %w(preferred admitted deprecated).include?(value)
+      value = "preferred"
+    end
+    @classification = value
+  end
+
+  # review-indicator
+  ## Must be one of the following <empty field> Under Review in Source Document",
+  def review_indicator=(value)
+    unless ["", "Under Review in Source Document"].include?(value)
+      value = ""
+    end
+    @review_indicator = value
+  end
+
+  # authoritative-source-similarity
+  #     ## Must be one of the following codes: identical = 1 restyled = 2 context added = 3 generalisation = 4 specialisation = 5 unspecified = 6",
+  def authoritative_source_similarity=(value)
+    unless (1..6).include?(value)
+      value = 6
+    end
+    @authoritative_source_similarity = value
+  end
+
+  # lineage-source-similarity
+  #     ## Must be one of the following codes: identical = 1 restyled = 2 context added = 3 generalisation = 4 specialisation = 5 unspecified = 6",
+  def authoritative_source_similarity=(value)
+    unless (1..6).include?(value)
+      value = 6
+    end
+    @authoritative_source_similarity
+  end
+
+  def review_status=(value) ## Must be one of pending tentative final
+    unless ["", "pending", "tentative", "final"].include?(value)
+      value = ""
+    end
+    @review_status = value
+  end
+
+  def review_type=(value)     ## Must be one of supersession, retirement
+    unless ["", "supersession", "retirement"].include?(value)
+      value = ""
+    end
+    @review_type = value
+  end
+
+  def review_decision=(value) ## Must be one of withdrawn, accepted notAccepted
+    unless ["", "withdrawn", "accepted", "notAccepted"].include?(value)
+      value = ""
+    end
+    @review_decision = value
+  end
+
+  def retired?
+    release >= 0
+  end
+
+end
+
+end

data/lib/tc211/termbase/term_workbook.rb

@@ -0,0 +1,53 @@
+
+require "creek"
+require "yaml"
+require "pathname"
+require_relative "information_sheet"
+require_relative "terminology_sheet"
+
+module Tc211::Termbase
+
+class TermWorkbook
+  attr_accessor :workbook
+  attr_accessor :glossary_info
+  attr_accessor :languages
+  attr_accessor :filename
+
+  SPECIAL_SHEETS = [
+    "Glossary Information",
+    "Character Encoding Spreadsheet"
+  ]
+
+  def initialize(filepath)
+    @filename = filepath
+    @workbook = Creek::Book.new(filepath)
+    @glossary_info = InformationSheet.new(find_sheet_by_name("Glossary Information"))
+    @languages = languages_supported
+    self
+  end
+
+  def languages_supported
+    @workbook.sheets.map(&:name).reject! do |name|
+      SPECIAL_SHEETS.include?(name)
+    end
+  end
+
+  def language_sheet(lang)
+    raise unless @languages.include?(lang)
+    TerminologySheet.new(find_sheet_by_name(lang))
+  end
+
+  def find_sheet_by_name(sheet_name)
+    @workbook.sheets.detect do |sheet|
+      sheet.name == sheet_name
+    end
+  end
+
+  def write_glossary_info
+    glossary_info_fn = Pathname.new(@filename).sub_ext(".yaml")
+    File.open(glossary_info_fn,"w") do |file|
+      file.write(glossary_info.to_yaml)
+    end
+  end
+end
+end

data/lib/tc211/termbase/terminology_sheet.rb

@@ -0,0 +1,79 @@
+require_relative "metadata_section"
+require_relative "terms_section"
+require "iso-639"
+
+module Tc211::Termbase
+
+class TerminologySheet
+  attr_accessor :sheet
+
+  def initialize(sheet)
+    @sheet = sheet
+    self
+  end
+
+  def language
+    @sheet.name
+  end
+
+  def language_code
+    # Hack to make ISO_639 gem work...
+    lang = case language
+    when "Dutch"
+      "Dutch; Flemish"
+    when "Spanish"
+      "Spanish; Castilian"
+    else
+      language
+    end
+    ISO_639.find_by_english_name(lang).alpha3
+  rescue
+    raise StandardError.new("Failed to find alpha3 code for language: #{lang}")
+  end
+
+  def sections_raw
+    # Sections either start with "A" => "Item", or they have empty lines between
+    raw_sections = @sheet.simple_rows.to_a
+
+    raw_sections.reject! do |section|
+      section.empty?
+    end
+
+    raw_sections = raw_sections.slice_before do |row|
+      row["A"].to_s == "Item" || row["A"].to_s.match(/^ISO 19135 Field/)
+    end.to_a
+  end
+
+  def terms_section
+    sections
+
+    sections.detect do |section|
+      section.is_a?(TermsSection)
+    end
+  end
+
+  def sections
+    return @sections if @sections
+
+    @sections = []
+    sections_raw.each_with_index do |x,i|
+
+      puts "--------- Section #{i} ------"
+      section = if MetadataSection.match_header(x[0])
+        puts "------ is a MetadataSection"
+        puts "rows: #{x.inspect}"
+        MetadataSection.new(x)
+      else
+        puts "------ is a TermsSection"
+        puts "rows: #{x.inspect}"
+        TermsSection.new(x, {language_code: language_code})
+      end
+
+      @sections << section
+    end
+
+  end
+
+end
+
+end

data/lib/tc211/termbase/terms_section.rb

@@ -0,0 +1,148 @@
+require_relative "sheet_section"
+require_relative "term"
+
+module Tc211::Termbase
+
+class TermsSection < SheetSection
+  attr_accessor :structure
+  attr_accessor :header_row
+
+  TERM_HEADER_ROW_MATCH = {
+    "A" => ["ISO 19135 Field\nRE_RegisterItem.itemIdentifier"],
+    "B" => ["ISO 19135 Field\nRE_RegisterItem.name"],
+    "C" => ["ISO 19135 Field\nRE_RegisterItem.\nalternativeExpression"],
+    "D" => ["Country_Code"],
+    # ... We don't need to match all the cells
+  }
+
+  TERM_BODY_COLUMN_MAP = {
+    "Term_ID" => "id",
+    "Term" => "term",
+    "Term [OPERATING LANGUAGE]" => "term",
+    "Term_Abbreviation" => "abbrev",
+    "Country code" => "country-code",
+    "Definition" => "definition",
+    "Term [OPERATING LANGUAGE - ALTERNATIVE CHARACTER SET]" => "alt",
+    "Term in English" => nil,
+    "Entry Status" => "entry-status",
+    ## Must be one of 'notValid' 'valid' 'superseded' 'retired'
+    "Term Clasification" => "classification",
+    ## Must be one of the following 'preferred' 'admitted' 'deprecated'
+    "Review Indicator" => "review-indicator",
+    ## Must be one of the following <empty field> 'Under Review in Source Document'",
+    "Authoritative Source" => "authoritative-source",
+    "Similarity to Authoritative Source" => "authoritative-source-similarity",
+    ## Must be one of the following codes: 'identical' = 1 'restyled' = 2 'context added' = 3 'generalisation' = 4 'specialisation' = 5 'unspecified' = 6",
+    "Lineage Source" => "lineage-source",
+    "Similarity to Lineage Source" => "lineage-source-similarity",
+    ## Must be one of the following codes: 'identical' = 1 'restyled' = 2 'context added' = 3 'generalisation' = 4 'specialisation' = 5 'unspecified' = 6",
+    "Term Synonyms" => "synonyms",
+    "Date Accepted" => "date-accepted", # yyyy-mm-dd,
+    "Date Amended" => "date-amended",   # yyyy-mm-dd,
+    "Review Date" => "review-date",     # yyyy-mm-dd,
+    "Review Status" => "review-status", ## Must be one of 'pending' 'tentative' 'final'",
+    "Review Type" => "review-type",     ## Must be one of 'supersession', 'retirement'",
+    "Review Decision" => "review-decision", ## Must be one of 'withdrawn', 'accepted' 'notAccepted'",
+    "Review Decision Date" => "review-decision-date", # yyyy-mm-dd
+    "Review Decision Event" => "review-decision-event",
+    "Review Decision Notes" => "review-decision-notes",
+    "Example_1" => "example-1",
+    "Note_1" => "note-1",
+    "Example_2" => "example-2",
+    "Note_2" => "note-2",
+    "Example_3" => "example-3",
+    "Note_3" => "note-3",
+    "Example_4" => "example-4",
+    "Note_4" => "note-4",
+    "Example_5" => "example-5",
+    "Note_5" => "note-5",
+    "Example_6" => "example-6",
+    "Note_6" => "note-6",
+    "Example_7" => "example-7",
+    "Note_7" => "note-7",
+    "Example_8" => "example-8",
+    "Note_8" => "note-8",
+    "Glossary Release" => "release"
+    ## Must be one of the following codes 'release1' = 1 'release1_retired' = -1 'release2' = 2 'release2_retired' = -2 etc "
+  }
+
+  def initialize(rows, options={})
+    super
+    raise StandardError.new("Does not match TermsSection header!") unless self.class.match_header(@rows[0])
+    @mapping_rows = @rows[0..1]
+    @header_row = @rows[2]
+    @body_rows = @rows[3..-1]
+    @language_code = options.delete(:language_code)
+    self
+  end
+
+  def structure
+    @structure ||= @header_row.inject({}) do |acc, (key, value)|
+      # puts "#{key}, #{value}, #{GLOSSARY_HEADER_TITLES[value]}"
+
+      # convert whitespace to a single space
+      cleaned_value = value.gsub(/\s+/, ' ')
+
+      matches = TERM_BODY_COLUMN_MAP.map do |key, value|
+        puts "key #{key}, value #{value}"
+        if cleaned_value[Regexp.new("^#{key}")]
+          [key, value]
+        end
+      end.compact
+
+      discard, longest_match_key = matches.max_by do |(a, b)|
+        a.length
+      end
+
+      # Here we need to skip "Term in English"
+      if key && longest_match_key
+        acc.merge!({ key => longest_match_key })
+      else
+        acc
+      end
+
+    end
+  end
+
+  def self.match_header(row)
+    # puts "row #{row}"
+    row.inject(true) do |acc, (key, value)|
+      # puts "#{key}, #{value}"
+      if TERM_HEADER_ROW_MATCH[key]
+        acc && TERM_HEADER_ROW_MATCH[key].include?(value)
+      else
+        acc
+      end
+    end
+  end
+
+  def parse_row(row)
+    return nil if row.empty?
+    attributes = {}
+
+    structure.each_pair do |key, value|
+      puts "#{key}, #{value}, #{row[key]}"
+      attribute_key = value
+      attribute_value = row[key]
+      next if attribute_value.nil?
+      attributes[attribute_key] = attribute_value
+    end
+
+    attributes
+  end
+
+  def terms
+    @terms ||= @body_rows.map do |row|
+      Term.new(parse_row(row).merge("language_code" => @language_code))
+    end
+  end
+
+  def to_hash
+    {
+      "terms" => terms.map(&:to_hash)
+    }
+  end
+
+end
+
+end

data/lib/tc211/termbase/version.rb

@@ -0,0 +1,5 @@
+module Tc211
+  module Termbase
+    VERSION = "0.1.0"
+  end
+end

data/tc211-termbase.gemspec

@@ -0,0 +1,31 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "tc211/termbase/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "tc211-termbase"
+  spec.version       = Tc211::Termbase::VERSION
+  spec.authors       = ["Ribose"]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = %q{Build scripts for the ISO/TC 211 Termbase}
+  spec.description   = %q{Build scripts for the ISO/TC 211 Termbase}
+  spec.homepage      = "https://open.ribose.com"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency "iso-639"
+  spec.add_runtime_dependency "creek"
+
+  spec.add_development_dependency "bundler", "~> 1.17"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,137 @@
+--- !ruby/object:Gem::Specification
+name: tc211-termbase
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Ribose
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-11-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: iso-639
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: creek
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: Build scripts for the ISO/TC 211 Termbase
+email:
+- open.source@ribose.com
+executables:
+- tc211-termbase-xlsx2yaml
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- Gemfile.lock
+- README.adoc
+- Rakefile
+- bin/console
+- bin/setup
+- exe/tc211-termbase-xlsx2yaml
+- lib/tc211/termbase.rb
+- lib/tc211/termbase/concept.rb
+- lib/tc211/termbase/concept_collection.rb
+- lib/tc211/termbase/information_sheet.rb
+- lib/tc211/termbase/metadata_section.rb
+- lib/tc211/termbase/sheet_section.rb
+- lib/tc211/termbase/term.rb
+- lib/tc211/termbase/term_workbook.rb
+- lib/tc211/termbase/terminology_sheet.rb
+- lib/tc211/termbase/terms_section.rb
+- lib/tc211/termbase/version.rb
+- tc211-termbase.gemspec
+homepage: https://open.ribose.com
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.7
+signing_key: 
+specification_version: 4
+summary: Build scripts for the ISO/TC 211 Termbase
+test_files: []